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

    Neuronpedia

    INDEX
    Explanations

    punctuation and pauses in dialogue

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     estekak
    -0.94
     myſelf
    -0.89
    ."</
    -0.88
    expandindo
    -0.86
     itſelf
    -0.84
    ."));
    -0.81
     Monfieur
    -0.80
    .";
    -0.80
     مشين
    -0.78
    ſelf
    -0.77
    POSITIVE LOGITS
    ?
    0.57
     of
    0.57
     (
    0.55
    start
    0.55
    ↵
    0.54
    -
    0.53
    ↵↵
    0.50
     ?
    0.50
     start
    0.50
     let
    0.50
    Act Density 0.009%

    No Known Activations