concept
active
concept:model-m4Model M4
Anonymous instruction-tuned LLM.
Neighborhood — ranked by edge-count
Findings (1)
finding
- Ambiguous anchors (33-27=60, 11-9=20) yield four distinct arithmetic interpretations across M1-M4associated_withModels produce different answers (240, 138, -240) from the same ambiguous prompt
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.
- Anonymous instruction-tuned LLM.
- Anonymous instruction-tuned LLM.
- Anonymous instruction-tuned LLM used in E1 ambiguous anchor test.
- A representation that captures relevant aspects of a system; according to the theorem, the regulator must embody this.
- Comparing models using log-evidence approximated by free energy.
- Large pretrained models used as backbones across tasks; their universality motivates the convergence hypothesis