Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dialogue punctuation

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on little stage-direction or emotion cues (e.g. parenthesized adverbs like “(nervously)”, “(laughs)”, “(whispers)”, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    dialogue between characters that reflects personal interactions and emotional conflicts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ipc
    -0.07
    困
    -0.07
    Neutral
    -0.06
    پ
    -0.06
     Wells
    -0.06
     même
    -0.06
    履
    -0.06
     disproportionate
    -0.06
     tys
    -0.06
     cherry
    -0.06
    POSITIVE LOGITS
    efeller
    0.06
    ocomplete
    0.06
    .ReadFile
    0.06
     setInterval
    0.06
     Hitch
    0.06
    [['
    0.06
     بازیگر
    0.06
     Cunning
    0.06
     Aug
    0.06
    .Reg
    0.06
    Act Density 0.044%

    No Known Activations