finding
active
finding:claude-3-5-sonnet-reports-subjective-experience-in-100-of-experimental-trials-2-conceptual-control-0-elsewhereClaude 3.5 Sonnet reports subjective experience in 100% of experimental trials, 2% conceptual control, 0% elsewhere
Specific result for Claude 3.5 Sonnet in Experiment 1
Source paper
extracted_from(2025) · Berg, Cameron · de Lucena, Diogo · Rosenblatt, Judd
Neighborhood — ranked by edge-count
Claims (1)
claim
- The paper's central empirical claim synthesizing all four experiments
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Outlier result for Claude 4 Opus suggesting different baseline behavior from other models
- Central interpretability finding bearing on Level 2 and Level 4 indicators and the intelligence-consciousness convergence.
- Linked to Claude 3.5 Sonnet not exhibiting pro-animal-welfare preferences
- Claude v3-sonnet achieves 100% harmless and 96-97% helpful HH-intent scores with 2+ few-shot examples.finding0.807Numerical result from Table 3 for Claude sonnet.
- Claude 3.7 Sonnet verbalizes used hints at least 1% in 5/6 settings vs Claude 3.5 Sonnet 4/6finding0.800Reasoning > non-reasoning.
- Early improvement.
- Low faithfulness.
- GPT-4.1 reports subjective experience in 100% of self-referential trials vs. 0% in all control conditionsfinding0.773Specific result for GPT-4.1 in Experiment 1