TY - CONF T1 - Confidence regulation neurons in language models JO - Advances in Neural Information Processing Systems UR - https://eprints.whiterose.ac.uk/id/eprint/222011 UR - https://neurips.cc/virtual/2024/poster/96903 PY - 2024/12/12 AU - Stolfo A AU - Wu B AU - Gurnee W AU - Belinkov Y AU - Song X AU - Sachan M AU - Nanda N ED - PB - NeurIPS Y2 - 2025/11/23 ER -