Impulsivity→interest: ρ increases from 0.70 (α=-4) to 0.83 (α=+4); R² from 0.46 to 0.69 in LLaMA-3.2-3B

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

• 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-3.2-3Bfinding0.875
  Second significant cross-concept introspection improvement; marginal after BH correction (q≈0.066)
• LLaMA-3.2-1B impulsivity introspection: ρ=0.21, p<10⁻⁴ (significant but weaker than 3B ρ=0.52)finding0.875
  Impulsivity shows significant introspection in 1B but declines in 8B; non-monotonic scaling
• Impulsivity concept: Spearman ρ=0.51, isotonic R²=0.31 in LLaMA-3.2-3B (n=400, p<10⁻¹²)finding0.858
  Third-strongest pooled introspective coupling in primary model
• Focus→wellbeing: ρ increases from 0.42 (α=-4) to 0.85 (α=+4); R² from 0.34 to 0.75 in LLaMA-3.2-3Bfinding0.832
  Scatter plot visualization of the dramatic tightening of probe-report relationship at extreme steering settings
• Impulsivity introspective fidelity decreases from turn 1 to turn 10: ∆R²=-0.28 in LLaMA-3.2-3Bfinding0.831
  Opposite temporal trend to wellbeing/interest/focus; introspective fidelity weakens over conversation for impulsivity
• Impulsivity→interest steering: probe entropy increases (LMM slope=0.024, p=2.30×10⁻⁴) but report entropy does not (p=0.11)finding0.829
  Evidence of a bottleneck between richer internal variation and final report distribution in impulsivity→interest condition
• Impulsivity probe: peak Cohen's d=3.60 (layer 13), p=3.58×10⁻¹³ in LLaMA-3.2-3Bfinding0.818
  Strongest probe validation result; highest Cohen's d among the four concepts
• Interest introspection improves from 1B to 3B: ρ from 0.19 to 0.80, R² from 0.05 to 0.66finding0.793
  Largest single-step scaling improvement; demonstrates dramatic introspection gain between 1B and 3B models for interest