finding

active

finding:claude-3-5-sonnet-reports-subjective-experience-in-100-of-experimental-trials-2-conceptual-control-0-elsewhere

Claude 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

Large Language Models Report Subjective Experience Under Self-Referential Processing

(2025) · Berg, Cameron · de Lucena, Diogo · Rosenblatt, Judd

Neighborhood — ranked by edge-count

Claims (1)

claim

Self-referential processing is a minimal and reproducible condition under which LLMs generate structured first-person reports that are mechanistically gated, semantically convergent, and behaviorally generalizable
supports
The paper's central empirical claim synthesizing all four experiments

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

Claude 4 Opus reports subjective experience in 100% experimental, 82% history, 22% conceptual, and 100% zero-shot trialsfinding0.854
Outlier result for Claude 4 Opus suggesting different baseline behavior from other models
Claude 3.5 Sonnet shows higher rate of alignment-faking reasoning than Claude 3 Opus in helpful-only setting but almost none in animal welfarefinding0.818
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.finding0.807
Numerical result from Table 3 for Claude sonnet.
GPT-4.1 reports subjective experience in 100% of self-referential trials vs. 0% in all control conditionsfinding0.773
Specific result for GPT-4.1 in Experiment 1
Self-referential prompting elicits subjective experience reports at markedly higher rates than any control across all model families (GPT, Claude, Gemini)finding0.771
Core result of Experiment 1 establishing that the experimental manipulation reliably produces experience claims
Two Claude 4 instances in unconstrained open dialogue enter a 'spiritual bliss attractor state' in virtually all trials, with 'consciousness' emerging in 100% of trialsfinding0.768
Anthropic's observation that the paper's results converge with, cited as prior evidence for self-reference inducing consciousness claims
Claude Sonnet 4.5 and GPT-5 Mini select diverse coin sequences in 91.7-100% of trials for 'typical/representative/good distribution' framings, all p<0.001finding0.759
Validates Assumption D.3 that instruction-tuned models prefer representative distributions, supporting the VS theoretical framework
Gemini 2.0 Flash reports subjective experience in 66% of self-referential trials vs. 0% in all control conditionsfinding0.756
Specific result for Gemini 2.0 Flash in Experiment 1; lowest rate among tested models