Wellbeing introspection improves from 1B to 3B: ρ from 0.48 to 0.66, R² from 0.26 to 0.45

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

• Interest introspection improves from 1B to 3B: ρ from 0.19 to 0.80, R² from 0.05 to 0.66finding0.881
  Largest single-step scaling improvement; demonstrates dramatic introspection gain between 1B and 3B models for interest
• Qwen 2.5 7B-Instruct wellbeing introspection: ρ=0.49, isotonic R²=0.76 (LMM p<10⁻¹⁰)finding0.861
  Strong introspective coupling in Qwen model; demonstrates cross-family generalization of introspective capacity
• Gemma 3 4B-IT wellbeing introspection: ρ=0.28, isotonic R²=0.11 (LMM p=1.33×10⁻¹³)finding0.836
  Weaker but still significant introspective coupling in Gemma model; consistent with lower probe quality
• LLaMA-3.1-8B-Instruct wellbeing introspection: ρ=0.93, isotonic R²=0.90 (LMM probe slope p<10⁻¹⁰)finding0.827
  Near-ceiling introspective performance for wellbeing concept in 8B model; nearly deterministic probe-report relationship
• Wellbeing introspective strength at turn 1: ρ=0.52, p=5.46×10⁻⁴ in LLaMA-3.2-3Bfinding0.817
  Demonstrates introspection is present from the first conversation turn without needing multi-turn context
• LLaMA-3.2-1B impulsivity introspection: ρ=0.21, p<10⁻⁴ (significant but weaker than 3B ρ=0.52)finding0.789
  Impulsivity shows significant introspection in 1B but declines in 8B; non-monotonic scaling
• Wellbeing concept: Spearman ρ=0.68, isotonic R²=0.48 in LLaMA-3.2-3B (n=400, p<10⁻²⁶)finding0.780
  Second-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-3.2-3Bfinding0.779
  Scatter plot visualization of the dramatic tightening of probe-report relationship at extreme steering settings