question
active
question:why-does-the-model-not-do-x-rather-than-why-does-it-do-xWhy does the model not do X rather than why does it do X?
A class of questions the method struggles with.
Neighborhood — ranked by edge-count
Papers (1)
paper
- On the Biology of a Large Language Modelassociated_withmentions
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Intro question.
- Key consequence: GPT's power comes from simulating something contingent.
- Self-explanation vs circuit.
- Future direction.
- Key jailbreak insight.
- Intro question.
- can we show that such graphs suitably represent the computation done by the model, and demonstrate their usefulness?question0.764Motivates case studies.
- noted as a possible confound