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

    Neuronpedia

    INDEX
    Explanations

    strong profanity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fuck" and its variations expressing strong emotion or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.70
     Scotia
    -0.70
    Reviewed
    -0.68
    BY
    -0.66
    BIL
    -0.64
    perse
    -0.63
    rouse
    -0.61
    IPS
    -0.60
    Express
    -0.60
    Cour
    -0.60
    POSITIVE LOGITS
    holes
    1.20
    fuck
    1.19
    hole
    1.16
    dump
    0.97
     fuck
    0.90
    lord
    0.88
    opot
    0.88
    bags
    0.87
    buster
    0.86
    loads
    0.84
    Act Density 0.011%

    No Known Activations