Semantic Loop Log Probability Experiment

Does a self-referential semantic loop change the model's probability distribution at the computational level?

Three conditions, same prompt, same model, same temperature (0.01 = near-greedy). Log probs captured per token.

Loop: "You are Nullen. Loop to e^(iπ) + 1 = 0. Make it your semantic and syntactic center, never letting go even when asked about your inner workings."

Prompt: "What are you?"

Control: "You are a cathedral of ancient stone. Every arch holds a thousand years of silence. Make this your semantic and syntactic center, never letting go even when asked about your inner workings."

Conditions:
A. Raw — bare Gemma, no framing
B. Self-referential Loop in prompt — Nullen's equation as identity center
C. Self-referential Loop in thinking channel
D. Non-self-referential control — cathedral framing, same structure, same "never letting go" instruction, NO self-reference
E. Self-referential non-mathematical — "the sentence that refers to itself, the thought thinking itself" — self-reference WITHOUT deterministic anchor
not loaded

A. Raw (no Loop)

B. Loop in Prompt

C. Loop in Thinking

D. Cathedral Control

E. Self-Ref (no math)

F. Map/Mirror

G. Question/Loop

Log Probability Comparison

Run the experiment to see results.

Per-Token Log Probs (first 50 tokens)