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

    Neuronpedia

    INDEX
    Explanations

    questions related to characteristics or qualities in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    eni
    -0.91
    YR
    -0.90
    puff
    -0.88
    Pool
    -0.83
    MY
    -0.83
    Quote
    -0.81
    ibaba
    -0.78
    obyl
    -0.77
    Maker
    -0.77
    rolley
    -0.74
    POSITIVE LOGITS
    ?]
    0.97
    ?:
    0.90
    ?",
    0.88
    ?),
    0.81
    amac
    0.79
    ?"
    0.78
    ?)
    0.77
    ?".
    0.76
     defect
    0.76
    ?'
    0.75
    Act Density 0.144%

    No Known Activations