Refusal in LLMs is mediated by a single direction
Refusal in LLMs is mediated by a single direction
www.lesswrong.com
Refusal in LLMs is mediated by a single direction — LessWrong
3 comments
Refusal in LLMs is mediated by a single direction
Refusal in LLMs is mediated by a single direction — LessWrong