claim
active
claim:studying-tasks-natural-to-pretrained-models-rather-than-to-human-investigators-yields-crisper-mechanismsStudying tasks natural to pretrained models rather than to human investigators yields crisper mechanisms
Methodological lesson.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Analogy to vision.
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.
- Highlights the non-genetic control of large-scale anatomy.
- Downside of abstraction.
- Interpretive claim built directly on the sorting-algorithm findings, central to the machine/organism symmetry argument.
- Extends ethical concern based on the collective nature of selves.
- Articulates why a one-layer transformer with MLP is the appropriate starting target for mechanistic interpretability
- Alternative hypothesis for how experience reports arise without explicit performance
- Interpretive claim about the mechanistic substrate of introspection in LLMs