Impulsivity probe: peak Cohen's d=3.60 (layer 13), p=3.58×10⁻¹³ in LLaMA-3.2-3B

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

• Interest probe: peak Cohen's d=1.67 (layer 14), p=9.45×10⁻⁶ in LLaMA-3.2-3Bfinding0.898
  Probe validation result confirming interest direction captures meaningful structure
• Wellbeing probe: peak Cohen's d=3.34 (layer 16), p=7.21×10⁻¹³ in LLaMA-3.2-3Bfinding0.870
  Probe validation result confirming wellbeing direction captures meaningful structure
• LLaMA-3.2-1B impulsivity introspection: ρ=0.21, p<10⁻⁴ (significant but weaker than 3B ρ=0.52)finding0.848
  Impulsivity shows significant introspection in 1B but declines in 8B; non-monotonic scaling
• Impulsivity→interest: ρ increases from 0.70 (α=-4) to 0.83 (α=+4); R² from 0.46 to 0.69 in LLaMA-3.2-3Bfinding0.818
  Scatter plot visualization showing strengthened probe-report relationship across alpha range
• Gemma 3 4B wellbeing probe: peak Cohen's d=1.8finding0.817
  Weaker cross-family probe; explains weaker introspection in Gemma
• Impulsivity concept: Spearman ρ=0.51, isotonic R²=0.31 in LLaMA-3.2-3B (n=400, p<10⁻¹²)finding0.812
  Third-strongest pooled introspective coupling in primary model
• Cross-concept steering: impulsivity→interest R² increases from 0.55 (α=-4) to 0.72 (α=+4), ∆R²=0.10, p=0.012 in LLaMA-3.2-3Bfinding0.798
  Second significant cross-concept introspection improvement; marginal after BH correction (q≈0.066)
• Impulsivity→interest steering: probe entropy increases (LMM slope=0.024, p=2.30×10⁻⁴) but report entropy does not (p=0.11)finding0.794
  Evidence of a bottleneck between richer internal variation and final report distribution in impulsivity→interest condition