paper / neel-nanda-2 / May 12 / failedWhat's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering
paper / neel-nanda-2 / May 9 / failedWhat's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering
paper / neel-nanda-2 / May 9 / failedCensored LLMs as a Natural Testbed for Secret Knowledge Elicitation