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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to legal and political contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    umbnails
    -0.69
    llor
    -0.64
    atives
    -0.64
    enture
    -0.60
    udeau
    -0.60
    eger
    -0.60
    ossom
    -0.59
     mentions
    -0.57
    isions
    -0.56
    IZE
    -0.56
    POSITIVE LOGITS
    nt
    0.96
     indeed
    0.93
     somehow
    0.86
     unlikely
    0.78
     not
    0.77
     going
    0.77
     worth
    0.75
     owed
    0.73
     gonna
    0.73
     destined
    0.73
    Act Density 16.370%

    No Known Activations