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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "devil" or something devilish

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of the devil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uries
    -0.79
    Ô
    -0.76
    yles
    -0.74
    dL
    -0.73
    ij士
    -0.73
    atern
    -0.72
    skirts
    -0.70
    POR
    -0.70
    Ģ
    -0.69
    µ
    -0.68
    POSITIVE LOGITS
    ishly
    1.20
     incarn
    0.92
    esses
    0.88
     worsh
    0.82
    ESS
    0.79
     devil
    0.79
     horns
    0.78
    ish
    0.77
     gou
    0.77
    ibur
    0.75
    Act Density 0.009%

    No Known Activations