Individual cone basis vectors may correspond to interpretable semantic facets of truth such as temporal facts, geographic facts, or commonsense

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Given a true propositional input (e.g., 'Paris is the capital of France'), ablating along any basis vector of this cone disrupts the model's ability to generate a truthful response.quote0.780
  Load-bearing illustration of what a concept cone for truth means operationally
• Concept cone truth interventions would generalize to larger frontier models and multimodal settingshypothesis0.759
  Key robustness question raised as future work
• Steering vectors discover effective triggers such as 'However' and 'Otherwise', consistent with prior reported reflection datasetsfinding0.755
  Validates that steering vectors capture reflection semantics by finding tokens reported in related work.
• In Qwen-2.5-9B, only v1 has meaningful cosine similarity to DIM direction; all additional basis vectors have cosine similarities ~1e-9finding0.750
  Appendix E replication of DIM alignment finding in Qwen model
• Anthropic Interpretability Team: 171 emotion vectors causally influence behavior; performing vs having functional emotion representation are measurably differentfinding0.749
  Cited as activation-level support for the performing care vs having care distinction the battery detects behaviorally
• There is a many-to-many mapping between neurons and concepts, meaning multiple high-level causal variables might be encoded in overlapping groups of neuronsclaim0.749
  Fundamental theoretical claim motivating DAS, attributed to Smolensky/Rumelhart/McClelland.
• Superposition hypothesis: neural networks represent more features than dimensions using almost-orthogonal directions.hypothesis0.746
  Explanation for why dictionary learning can recover many more features than dimensions.
• Truth may be linearly separable in the model's representation space, but the structure is richer than a single linear axisclaim0.745
  Interpretive synthesis of DIM and cone intervention successes