Random vector baseline

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

• Random and negated vectors less effective than concept vectorsfinding0.740
  Random vectors require larger norm to trigger detection (8 vs 2); elicit awareness at lower rates (9/100); negated vectors comparably effective but model identification confabulated.
• Orthonormal Basis Vectorsconcept0.740
  The set of mutually orthogonal unit vectors that span the concept cone, each independently causally mediating target behavior
• Prompt-Label Baselinemethod0.739
  Conditional generation on explicit Big Five labels using per-dimension descriptors; used as inference-time baseline
• Stitch (baseline)method0.734
  Baseline model stitching trained in a single behavioral direction without CL auxiliary loss, used for comparison with CLMAS.
• Residual Activation Vectorsconcept0.733
  Layer-40 activations with the component explained by compressed Gemini embeddings subtracted, isolating information not driven by surface text content
• Natural trait (expressed at baseline)concept0.733
  A trait already strongly expressed at baseline (alpha=0) without steering intervention
• baseline control experimentmethod0.729
  Control using objectively-NO factual questions under identical injection to measure global logit shift vs. genuine detection signal
• No-Steering Baseline Experimentmethod0.729
  Control condition with steering disabled to confirm self-correction is induced by steering, not spontaneous