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

    Neuronpedia

    INDEX
    Explanations

    narratives of criminal activities or violent actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.93
    ratulations
    -0.89
    cule
    -0.82
    video
    -0.81
    monary
    -0.81
    endiary
    -0.80
    perty
    -0.77
    idav
    -0.75
    xual
    -0.74
    itudinal
    -0.71
    POSITIVE LOGITS
     afar
    1.19
     whence
    1.16
     scratch
    1.00
     abroad
    0.99
     thence
    0.94
     somewhere
    0.83
     anywhere
    0.81
     Palest
    0.75
     underneath
    0.75
     beneath
    0.71
    Act Density 0.177%

    No Known Activations