---
title: "Unveiling Language Competence Neurons — Duan 2025"
description: "This offers causal evidence that these abilities depend on identifiable neurons. 44 references, cited by 8 papers here."
authors: ["Xufeng Duan", "Xinyu Zhou", "Bei Xiao", "Zhenguang Cai"]
year: 2025
venue: "Proceedings of the 31st International Conference on Computational Linguistics"
source: "https://aclanthology.org/2025.coling-main.677/"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/duan-2025-unveiling-language-competence-neurons-psycholinguistic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/duan-2025-unveiling-language-competence-neurons-psycholinguistic/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/2/) / Unveiling Language Competence Neurons: A Psycholinguistic Approach to Model Interpretability

# Unveiling Language Competence Neurons: A Psycholinguistic Approach to Model Interpretability

**Authors:** Xufeng Duan, Xinyu Zhou, Bei Xiao and [Zhenguang Cai](https://md.research.elamur.ai/free/en/authors/zhenguang-cai/) · **Year:** 2025 · **Venue:** Proceedings of the 31st International Conference on Computational Linguistics · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.coling-main.677/) · [PDF](https://aclanthology.org/2025.coling-main.677.pdf) · [OpenAlex](https://openalex.org/W4403786792)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 8 in our library, of the 140,884 papers whose bibliographies we read

## Summary
Large language models often respond like people in psycholinguistic experiments, but it remains unclear which internal units support these abilities. Duan et al. ask whether such competence in GPT-2-XL can be traced to individual neurons. They adapt three English paradigms from Cai et al. (2024): sound-shape association, sound-gender association and implicit causality. For each task, the stimuli are split in half. One half is used to rank neurons by their accumulated direct effect on the logit gap between a target token and a distractor. The other half is held out to test what happens when the top-ranked neurons are disabled or have their activations doubled.

GPT-2-XL does not reproduce the human sound-shape pattern, and manipulating neurons in that task has no significant effect. In the sound-gender and implicit causality tasks, the model behaves more like humans, and altering the selected neurons changes its outputs. This offers causal evidence that these abilities depend on identifiable neurons. The authors frame the work as the first neuron-level study of language competence grounded in psycholinguistic experiments.

## Key points
- **Model and tasks:** The model is GPT-2-XL, tested on three English tasks adapted from Cai et al. (2024).
  - Sound-shape association uses 20 pairs of novel words in the style of kiki/bouba and takete/maluma.
  - Sound-gender association links phonology to gender.
  - Implicit causality concerns verb-driven causal role assignment.
- **Method:**
  - Stimuli are divided evenly into probing and testing sets.
  - Neurons are chosen by accumulative direct effect on the target-versus-distractor logit difference.
  - The top 5 or 50 neurons are then ablated or their activations doubled.
- **Sound-shape result:** The model fails to show the human association, and neuron manipulation has no significant effect, which suggests no specialized neurons exist for this ability.
- **Other two tasks:** The model only marginally replicates the human sound-gender tendency but performs human-like on implicit causality. In both tasks, manipulating the selected neurons significantly shifts its predictions.
- **Limitations:**
  - Only a single, relatively old model was examined, chosen due to compute constraints, with newer models such as Llama 3.2 named for future work.
  - Just three phenomena were tested.
  - Manipulating individual neurons may miss distributed representations.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

Topics: [🧒 Psycholinguistics & language acquisition](https://md.research.elamur.ai/free/en/topics/psycholinguistics/) · [🔬 Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/)

## Cite

Cite as: Xufeng Duan, Xinyu Zhou, Bei Xiao and Zhenguang Cai. 2025. Unveiling Language Competence Neurons: A Psycholinguistic Approach to Model Interpretability. Proceedings of the 31st International Conference on Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{duan2025unveiling,
  title = {{Unveiling Language Competence Neurons: A Psycholinguistic Approach to Model Interpretability}},
  author = {Xufeng Duan, Xinyu Zhou, Bei Xiao and Zhenguang Cai},
  booktitle = {Proceedings of the 31st International Conference on Computational Linguistics},
  year = {2025},
  url = {https://aclanthology.org/2025.coling-main.677/}
}
```

- [← previous Survey of Abstract Meaning Representation: Then, Now, Future](https://md.research.elamur.ai/free/en/papers/mansouri-2025-survey-abstract-meaning-representation-then/)
- [next → A Comprehensive Evaluation of Large Language Models on Mental Illnesses in Arabic Context](https://md.research.elamur.ai/free/en/papers/zahran-2025-comprehensive-evaluation-large-language-models/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/2/)

## References

44 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Badr AlKhamissi, Greta Tuckute, Antoine Bosselut, and Martin Schrimpf. 2024. The llm language network: A neuroscientific approach for identifying causally task-relevant units. arXiv preprint arXiv:2411.02280. [find](https://scholar.google.com/scholar?q=Badr+AlKhamissi%2C+Greta+Tuckute%2C+Antoine+Bosselut%2C+and+Martin+Schrimpf%2E+2024%2E+The+llm+language+network%3A+A+neuroscientific+approach+for+identifying+causally+task%2Drelevant+units%2E+arXiv+preprint+arXiv%3A241)
2. Leila Arras, Ahmed Osman, Klaus-Robert Müller, and Wojciech Samek. 2019. Evaluating Recurrent Neural Network Explanations. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 113– 126, Florence, Italy. Association for Computational Linguisti… [find](https://scholar.google.com/scholar?q=Leila+Arras%2C+Ahmed+Osman%2C+Klaus%2DRobert+M%C3%BCller%2C+and+Wojciech+Samek%2E+2019%2E+Evaluating+Recurrent+Neural+Network+Explanations%2E+In+Proceedings+of+the+2019+ACL+Workshop+BlackboxNLP%3A+Analyzing+and+Interpreti)
3. David Bau, Jun-Yan Zhu, Hendrik Strobelt, Agata Lapedriza, Bolei Zhou, and Antonio Torralba. 2020. Understanding the role of individual units in a deep neural network. Proceedings of the National Academy of Sciences, 117(48):30071–30078. [find](https://scholar.google.com/scholar?q=David+Bau%2C+Jun%2DYan+Zhu%2C+Hendrik+Strobelt%2C+Agata+Lapedriza%2C+Bolei+Zhou%2C+and+Antonio+Torralba%2E+2020%2E+Understanding+the+role+of+individual+units+in+a+deep+neural+network%2E+Proceedings+of+the+National+Acad)
4. T. Bricken, A. Templeton, J. Batson, B. Chen, A. Jermyn, T. Conerly, N. Turner, C. Anil, C. Denison, A. Askell, R. Lasenby, Y. Wu, S. Kravec, N. Schiefer, T. Maxwell, N. Joseph, Z. Hatfield-Dodds, A. Tamkin, K. Nguyen, B. McLean, J.E. Burke, T. Hume, S. Carter, T. Henighan, and C. Olah. 2023. Toward… [find](https://scholar.google.com/scholar?q=T%2E+Bricken%2C+A%2E+Templeton%2C+J%2E+Batson%2C+B%2E+Chen%2C+A%2E+Jermyn%2C+T%2E+Conerly%2C+N%2E+Turner%2C+C%2E+Anil%2C+C%2E+Denison%2C+A%2E+Askell%2C+R%2E+Lasenby%2C+Y%2E+Wu%2C+S%2E+Kravec%2C+N%2E+Schiefer%2C+T%2E+Maxwell%2C+N%2E+Joseph%2C+Z%2E+Hatfield%2DDodds%2C+A%2E+)
5. Zhenguang G. Cai, Xufeng Duan, David A. Haslett, Shuqi Wang, and Martin J. Pickering. 2024. Do large language models resemble humans in language use? arXiv preprint. ArXiv:2303.08014 [cs]. [find](https://scholar.google.com/scholar?q=Zhenguang+G%2E+Cai%2C+Xufeng+Duan%2C+David+A%2E+Haslett%2C+Shuqi+Wang%2C+and+Martin+J%2E+Pickering%2E+2024%2E+Do+large+language+models+resemble+humans+in+language+use%3F+arXiv+preprint%2E+ArXiv%3A2303%2E08014+%5Bcs%5D%2E)
6. Kimberly Wright Cassidy, Michael H Kelly, and Lee’at J Sharoni. 1999. Inferring gender from name phonology. Journal of Experimental Psychology: General, 128(3):362. [find](https://scholar.google.com/scholar?q=Kimberly+Wright+Cassidy%2C+Michael+H+Kelly%2C+and+Lee%E2%80%99at+J+Sharoni%2E+1999%2E+Inferring+gender+from+name+phonology%2E+Journal+of+Experimental+Psychology%3A+General%2C+128%283%29%3A362%2E)
7. Kevin Clark, Urvashi Khandelwal, Omer Levy, and Christopher D. Manning. 2019. What Does BERT Look At? An Analysis of BERT’s Attention. arXiv preprint. ArXiv:1906.04341 [cs]. [find](https://scholar.google.com/scholar?q=Kevin+Clark%2C+Urvashi+Khandelwal%2C+Omer+Levy%2C+and+Christopher+D%2E+Manning%2E+2019%2E+What+Does+BERT+Look+At%3F+An+Analysis+of+BERT%E2%80%99s+Attention%2E+arXiv+preprint%2E+ArXiv%3A1906%2E04341+%5Bcs%5D%2E)
8. Ishita Dasgupta, Andrew K. Lampinen, Stephanie C. Y. Chan, Hannah R. Sheahan, Antonia Creswell, Dharshan Kumaran, James L. McClelland, and Felix Hill. 2023. Language models show human-like content effects on reasoning tasks. arXiv preprint. ArXiv:2207.07051 [cs]. [find](https://scholar.google.com/scholar?q=Ishita+Dasgupta%2C+Andrew+K%2E+Lampinen%2C+Stephanie+C%2E+Y%2E+Chan%2C+Hannah+R%2E+Sheahan%2C+Antonia+Creswell%2C+Dharshan+Kumaran%2C+James+L%2E+McClelland%2C+and+Felix+Hill%2E+2023%2E+Language+models+show+human%2Dlike+content+eff)
9. Dorottya Demszky, Diyi Yang, David S. Yeager, Christopher J. Bryan, Margarett Clapper, Susannah Chandhok, Johannes C. Eichstaedt, Cameron Hecht, Jeremy Jamieson, Meghann Johnson, Michaela Jones, Danielle Krettek-Cobb, Leslie Lai, Nirel JonesMitchell, Desmond C. Ong, Carol S. Dweck, James J. Gross, a… [find](https://scholar.google.com/scholar?q=Dorottya+Demszky%2C+Diyi+Yang%2C+David+S%2E+Yeager%2C+Christopher+J%2E+Bryan%2C+Margarett+Clapper%2C+Susannah+Chandhok%2C+Johannes+C%2E+Eichstaedt%2C+Cameron+Hecht%2C+Jeremy+Jamieson%2C+Meghann+Johnson%2C+Michaela+Jones%2C+Danie)
10. Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Baobao Chang, Xu Sun, Lei Li, and Zhifang Sui. 2024. A Survey on In-context Learning. arXiv preprint. ArXiv:2301.00234 [cs]. [our card](https://md.research.elamur.ai/free/en/papers/dong-2023-survey-context-learning/)
11. Xufeng Duan, Shixuan Li, and Zhenguang G Cai. 2024a. Macbehaviour: An r package for behavioural experimentation on large language models. arXiv preprint arXiv:2405.07495. — [arXiv:2405.07495](https://arxiv.org/abs/2405.07495) [find](https://scholar.google.com/scholar?q=Xufeng+Duan%2C+Shixuan+Li%2C+and+Zhenguang+G+Cai%2E+2024a%2E+Macbehaviour%3A+An+r+package+for+behavioural+experimentation+on+large+language+models%2E+arXiv+preprint+arXiv%3A2405%2E07495%2E+%E2%80%94+%5BarXiv%3A2405%2E07495%5D%28https%3A%2F%2F)
12. Xufeng Duan, Bei Xiao, Xuemei Tang, and Zhenguang G Cai. 2024b. Hlb: Benchmarking llms’ humanlikeness in language use. arXiv preprint arXiv:2409.15890. — [arXiv:2409.15890](https://arxiv.org/abs/2409.15890) [find](https://scholar.google.com/scholar?q=Xufeng+Duan%2C+Bei+Xiao%2C+Xuemei+Tang%2C+and+Zhenguang+G+Cai%2E+2024b%2E+Hlb%3A+Benchmarking+llms%E2%80%99+humanlikeness+in+language+use%2E+arXiv+preprint+arXiv%3A2409%2E15890%2E+%E2%80%94+%5BarXiv%3A2409%2E15890%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2409%2E)
13. Nelson Elhage, Tristan Hume, Catherine Olsson, Nicholas Schiefer, Tom Henighan, Shauna Kravec, Zac Hatfield-Dodds, Robert Lasenby, Dawn Drain, Carol Chen, Roger Grosse, Sam McCandlish, Jared Kaplan, Dario Amodei, Martin Wattenberg, and Christopher Olah. 2022. Toy Models of Superposition. arXiv prepr… [find](https://scholar.google.com/scholar?q=Nelson+Elhage%2C+Tristan+Hume%2C+Catherine+Olsson%2C+Nicholas+Schiefer%2C+Tom+Henighan%2C+Shauna+Kravec%2C+Zac+Hatfield%2DDodds%2C+Robert+Lasenby%2C+Dawn+Drain%2C+Carol+Chen%2C+Roger+Grosse%2C+Sam+McCandlish%2C+Jared+Kaplan%2C+D)
14. Nelson Elhage, Neel Nanda, Catherine Olsson, Tom Henighan, Nicholas Joseph, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, et al. 2021. A mathematical framework for transformer circuits. Transformer Circuits Thread, 1(1):12. [find](https://scholar.google.com/scholar?q=Nelson+Elhage%2C+Neel+Nanda%2C+Catherine+Olsson%2C+Tom+Henighan%2C+Nicholas+Joseph%2C+Ben+Mann%2C+Amanda+Askell%2C+Yuntao+Bai%2C+Anna+Chen%2C+Tom+Conerly%2C+et+al%2E+2021%2E+A+mathematical+framework+for+transformer+circuits%2E)
15. Allyson Ettinger. 2020. What bert is not: Lessons from a new suite of psycholinguistic diagnostics for language models. Transactions of the Association for Computational Linguistics, 8:34–48. [our card](https://md.research.elamur.ai/free/en/papers/ettinger-2020-what-bert-is-not-lessons/)
16. R Futrell. 2019. Neural language models as psycholinguistic subjects: Representations of syntactic state. arXiv preprint arXiv:1903.03260. [our card](https://md.research.elamur.ai/free/en/papers/futrell-2019-neural-language-models-as-psycholinguistic/)
17. Catherine Garvey and Alfonso Caramazza. 1974. Implicit causality in verbs. Linguistic inquiry, 5(3):459– 464. [find](https://scholar.google.com/scholar?q=Catherine+Garvey+and+Alfonso+Caramazza%2E+1974%2E+Implicit+causality+in+verbs%2E+Linguistic+inquiry%2C+5%283%29%3A459%E2%80%93+464%2E)
18. Thilo Hagendorff. 2023. Machine Psychology: Investigating Emergent Capabilities and Behavior in Large Language Models Using Psychological Methods. arXiv preprint. ArXiv:2303.13988 [cs]. — [arXiv:2303.13988](https://arxiv.org/abs/2303.13988) [find](https://scholar.google.com/scholar?q=Thilo+Hagendorff%2E+2023%2E+Machine+Psychology%3A+Investigating+Emergent+Capabilities+and+Behavior+in+Large+Language+Models+Using+Psychological+Methods%2E+arXiv+preprint%2E+ArXiv%3A2303%2E13988+%5Bcs%5D%2E+%E2%80%94+%5BarXiv%3A2303%2E)
19. Jennifer Hu, Sammy Floyd, Olessia Jouravlev, Evelina Fedorenko, and Edward Gibson. 2022. A fine-grained comparison of pragmatic language understanding in humans and language models. arXiv preprint arXiv:2212.06801. [our card](https://md.research.elamur.ai/free/en/papers/hu-2023-fine-grained-comparison-pragmatic-language/)
20. Kuan-Jung Huang, Suhas Arehalli, Mari Kugemoto, Christian Muxica, Grusha Prasad, Brian Dillon, and Tal Linzen. 2024. Large-scale benchmark yields no evidence that language model surprisal explains syntactic disambiguation difficulty. Journal of Memory and Language, 137:104510. [find](https://scholar.google.com/scholar?q=Kuan%2DJung+Huang%2C+Suhas+Arehalli%2C+Mari+Kugemoto%2C+Christian+Muxica%2C+Grusha+Prasad%2C+Brian+Dillon%2C+and+Tal+Linzen%2E+2024%2E+Large%2Dscale+benchmark+yields+no+evidence+that+language+model+surprisal+explains+syn)
21. Wolfgang Köhler. 1967. Gestalt psychology. Psychologische forschung, 31(1):XVIII–XXX. [find](https://scholar.google.com/scholar?q=Wolfgang+K%C3%B6hler%2E+1967%2E+Gestalt+psychology%2E+Psychologische+forschung%2C+31%281%29%3AXVIII%E2%80%93XXX%2E)
22. Yongjie Lin, Yi Chern Tan, and Robert Frank. 2019. Open Sesame: Getting inside BERT’s Linguistic Knowledge. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 241–253, Florence, Italy. Association for Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/lin-2019-open-sesame-getting-inside-bert/)
23. James A. Michaelov and Benjamin K. Bergen. 2023. Emergent inabilities? Inverse scaling over the course of pretraining. arXiv preprint. ArXiv:2305.14681 [cs]. [find](https://scholar.google.com/scholar?q=James+A%2E+Michaelov+and+Benjamin+K%2E+Bergen%2E+2023%2E+Emergent+inabilities%3F+Inverse+scaling+over+the+course+of+pretraining%2E+arXiv+preprint%2E+ArXiv%3A2305%2E14681+%5Bcs%5D%2E)
24. Dan Mossing, Steven Bills, Henk Tillman, Tom Dupré la Tour, Nick Cammarata, Leo Gao, Joshua Achiam, Catherine Yeh, Jan Leike, Jeff Wu, and William Saunders. 2024. Transformer debugger. [https://github.com/openai/transformer-debugger](https://github.com/openai/transformer-debugger). [↗](https://github.com/openai/transformer-debugger)
25. Jesse Mu and Jacob Andreas. 2020. Compositional explanations of neurons. Advances in Neural Information Processing Systems, 33:17153–17163. [find](https://scholar.google.com/scholar?q=Jesse+Mu+and+Jacob+Andreas%2E+2020%2E+Compositional+explanations+of+neurons%2E+Advances+in+Neural+Information+Processing+Systems%2C+33%3A17153%E2%80%9317163%2E)
26. Catherine Olsson, Nelson Elhage, Neel Nanda, Nicholas Joseph, Nova DasSarma, Tom Henighan, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, et al. 2022. In-context learning and induction heads. arXiv preprint arXiv:2209.11895. [find](https://scholar.google.com/scholar?q=Catherine+Olsson%2C+Nelson+Elhage%2C+Neel+Nanda%2C+Nicholas+Joseph%2C+Nova+DasSarma%2C+Tom+Henighan%2C+Ben+Mann%2C+Amanda+Askell%2C+Yuntao+Bai%2C+Anna+Chen%2C+et+al%2E+2022%2E+In%2Dcontext+learning+and+induction+heads%2E+arXiv+p)
27. Zhuang Qiu, Xufeng Duan, and Zhenguang Cai. 2024. Evaluating grammatical well-formedness in large language models: A comparative study with human judgments. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 189– 198, Bangkok, Thailand. Association for Computat… [find](https://scholar.google.com/scholar?q=Zhuang+Qiu%2C+Xufeng+Duan%2C+and+Zhenguang+Cai%2E+2024%2E+Evaluating+grammatical+well%2Dformedness+in+large+language+models%3A+A+comparative+study+with+human+judgments%2E+In+Proceedings+of+the+Workshop+on+Cognitive)
28. Zhuang Qiu, Xufeng Duan, and Zhenguang Garry Cai. 2023. Pragmatic Implicature Processing in ChatGPT. [find](https://scholar.google.com/scholar?q=Zhuang+Qiu%2C+Xufeng+Duan%2C+and+Zhenguang+Garry+Cai%2E+2023%2E+Pragmatic+Implicature+Processing+in+ChatGPT%2E)
29. Qualtrics. 2024. Qualtrics and all other qualtrics product or service names are registered trademarks or trademarks of qualtrics. Provo, UT, USA. [find](https://scholar.google.com/scholar?q=Qualtrics%2E+2024%2E+Qualtrics+and+all+other+qualtrics+product+or+service+names+are+registered+trademarks+or+trademarks+of+qualtrics%2E+Provo%2C+UT%2C+USA%2E)
30. Philip Quirke, Clement Neo, and Fazl Barez. 2024. Increasing trust in language models through the reuse of verified circuits. arXiv preprint arXiv:2402.02619. — [arXiv:2402.02619](https://arxiv.org/abs/2402.02619) [find](https://scholar.google.com/scholar?q=Philip+Quirke%2C+Clement+Neo%2C+and+Fazl+Barez%2E+2024%2E+Increasing+trust+in+language+models+through+the+reuse+of+verified+circuits%2E+arXiv+preprint+arXiv%3A2402%2E02619%2E+%E2%80%94+%5BarXiv%3A2402%2E02619%5D%28https%3A%2F%2Farxiv%2Eorg%2Fab)
31. Tilman Räuker, Anson Ho, Stephen Casper, and Dylan Hadfield-Menell. 2023. Toward transparent ai: A survey on interpreting the inner structures of deep neural networks. In 2023 ieee conference on secure and trustworthy machine learning (satml), pages 464– 483. IEEE. [find](https://scholar.google.com/scholar?q=Tilman+R%C3%A4uker%2C+Anson+Ho%2C+Stephen+Casper%2C+and+Dylan+Hadfield%2DMenell%2E+2023%2E+Toward+transparent+ai%3A+A+survey+on+interpreting+the+inner+structures+of+deep+neural+networks%2E+In+2023+ieee+conference+on+secur)
32. Jie Ren, Qipeng Guo, Hang Yan, Dongrui Liu, Quanshi Zhang, Xipeng Qiu, and Dahua Lin. 2024. Identifying semantic induction heads to understand in-context learning. arXiv preprint arXiv:2402.13055. [find](https://scholar.google.com/scholar?q=Jie+Ren%2C+Qipeng+Guo%2C+Hang+Yan%2C+Dongrui+Liu%2C+Quanshi+Zhang%2C+Xipeng+Qiu%2C+and+Dahua+Lin%2E+2024%2E+Identifying+semantic+induction+heads+to+understand+in%2Dcontext+learning%2E+arXiv+preprint+arXiv%3A2402%2E13055%2E)
33. Ran Song, Shizhu He, Shuting Jiang, Yantuan Xian, Shengxiang Gao, Kang Liu, and Zhengtao Yu. 2024. Does large language model contain task-specific neurons? In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7101–7113, Miami, Florida, USA. Association for… [find](https://scholar.google.com/scholar?q=Ran+Song%2C+Shizhu+He%2C+Shuting+Jiang%2C+Yantuan+Xian%2C+Shengxiang+Gao%2C+Kang+Liu%2C+and+Zhengtao+Yu%2E+2024%2E+Does+large+language+model+contain+task%2Dspecific+neurons%3F+In+Proceedings+of+the+2024+Conference+on+Emp)
34. Massimo Stella, Thomas T Hills, and Yoed N Kenett. 2023. Using cognitive psychology to understand gpt-like models needs to extend beyond human biases. Proceedings of the National Academy of Sciences, 120(43):e2312911120. [find](https://scholar.google.com/scholar?q=Massimo+Stella%2C+Thomas+T+Hills%2C+and+Yoed+N+Kenett%2E+2023%2E+Using+cognitive+psychology+to+understand+gpt%2Dlike+models+needs+to+extend+beyond+human+biases%2E+Proceedings+of+the+National+Academy+of+Sciences%2C+)
35. Tianyi Tang, Wenyang Luo, Haoyang Huang, Dongdong Zhang, Xiaolei Wang, Xin Zhao, Furu Wei, and Ji-Rong Wen. 2024. Language-specific neurons: The key to multilingual capabilities in large language models. arXiv preprint arXiv:2402.16438. [our card](https://md.research.elamur.ai/free/en/papers/tang-2024-language-specific-neurons-key-multilingual/)
36. Adly Templeton. 2024. Scaling monosemanticity: Extracting interpretable features from claude 3 sonnet. Anthropic. [find](https://scholar.google.com/scholar?q=Adly+Templeton%2E+2024%2E+Scaling+monosemanticity%3A+Extracting+interpretable+features+from+claude+3+sonnet%2E+Anthropic%2E)
37. Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian, Daniel Nevo, Yaron Singer, and Stuart Shieber. 2020. Investigating gender bias in language models using causal mediation analysis. Advances in neural information processing systems, 33:12388– 12401. [find](https://scholar.google.com/scholar?q=Jesse+Vig%2C+Sebastian+Gehrmann%2C+Yonatan+Belinkov%2C+Sharon+Qian%2C+Daniel+Nevo%2C+Yaron+Singer%2C+and+Stuart+Shieber%2E+2020%2E+Investigating+gender+bias+in+language+models+using+causal+mediation+analysis%2E+Advance)
38. Kevin Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, and Jacob Steinhardt. 2022. Interpretability in the wild: a circuit for indirect object identification in gpt-2 small. arXiv preprint arXiv:2211.00593. [find](https://scholar.google.com/scholar?q=Kevin+Wang%2C+Alexandre+Variengien%2C+Arthur+Conmy%2C+Buck+Shlegeris%2C+and+Jacob+Steinhardt%2E+2022%2E+Interpretability+in+the+wild%3A+a+circuit+for+indirect+object+identification+in+gpt%2D2+small%2E+arXiv+preprint+ar)
39. Shuqi Wang, Xufeng Duan, and Zhenguang Cai. 2024a. A multimodal large language model “foresees” objects based on verb information but not gender. In Proceedings of the 28th Conference on Computational Natural Language Learning, pages 435–441, Miami, FL, USA. Association for Computational Linguistics… [find](https://scholar.google.com/scholar?q=Shuqi+Wang%2C+Xufeng+Duan%2C+and+Zhenguang+Cai%2E+2024a%2E+A+multimodal+large+language+model+%E2%80%9Cforesees%E2%80%9D+objects+based+on+verb+information+but+not+gender%2E+In+Proceedings+of+the+28th+Conference+on+Computational)
40. Weixuan Wang, Barry Haddow, Minghao Wu, Wei Peng, and Alexandra Birch. 2024b. Sharing matters: Analysing neurons across languages and tasks in llms. arXiv preprint arXiv:2406.09265. — [arXiv:2406.09265](https://arxiv.org/abs/2406.09265) [find](https://scholar.google.com/scholar?q=Weixuan+Wang%2C+Barry+Haddow%2C+Minghao+Wu%2C+Wei+Peng%2C+and+Alexandra+Birch%2E+2024b%2E+Sharing+matters%3A+Analysing+neurons+across+languages+and+tasks+in+llms%2E+arXiv+preprint+arXiv%3A2406%2E09265%2E+%E2%80%94+%5BarXiv%3A2406%2E0926)
41. Alex Warstadt, Amanpreet Singh, and Samuel R. Bowman. 2019. Neural Network Acceptability Judgments. Transactions of the Association for Computational Linguistics, 7:625–641. Place: Cambridge, MA Publisher: MIT Press. [find](https://scholar.google.com/scholar?q=Alex+Warstadt%2C+Amanpreet+Singh%2C+and+Samuel+R%2E+Bowman%2E+2019%2E+Neural+Network+Acceptability+Judgments%2E+Transactions+of+the+Association+for+Computational+Linguistics%2C+7%3A625%E2%80%93641%2E+Place%3A+Cambridge%2C+MA+Publi)
42. Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022. Emergent Abilities of Large Language Models. arXiv preprint. Ar… [our card](https://md.research.elamur.ai/free/en/papers/wei-2022-emergent-abilities-large-language-models/)
43. Zhihao Zhang, Jun Zhao, Qi Zhang, Tao Gui, and Xuanjing Huang. 2024. Unveiling Linguistic Regions in Large Language Models. arXiv preprint. ArXiv:2402.14700 [cs]. [find](https://scholar.google.com/scholar?q=Zhihao+Zhang%2C+Jun+Zhao%2C+Qi+Zhang%2C+Tao+Gui%2C+and+Xuanjing+Huang%2E+2024%2E+Unveiling+Linguistic+Regions+in+Large+Language+Models%2E+arXiv+preprint%2E+ArXiv%3A2402%2E14700+%5Bcs%5D%2E)
44. Xinyu Zhou, Delong Chen, Samuel Cahyawijaya, Xufeng Duan, and Zhenguang G Cai. 2024. Linguistic minimal pairs elicit linguistic similarity in large language models. arXiv preprint arXiv:2409.12435. [find](https://scholar.google.com/scholar?q=Xinyu+Zhou%2C+Delong+Chen%2C+Samuel+Cahyawijaya%2C+Xufeng+Duan%2C+and+Zhenguang+G+Cai%2E+2024%2E+Linguistic+minimal+pairs+elicit+linguistic+similarity+in+large+language+models%2E+arXiv+preprint+arXiv%3A2409%2E12435%2E)