@article{thehydraeffectemergentselfrepairin, title = {The Hydra Effect: Emergent Self-repair in Language Model Computations}, author = {Thomas McGrath and Matthew Rahtz and Janos Kramar and Vladimir Mikulik and Shane Legg}, year = {2023}, eprint = {2307.15771}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2307.15771v1}, }