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

    Neuronpedia

    INDEX
    Explanations

    profane language

    oai_token-act-pair · gpt-3.5-turbo

    the expletive "fuck" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BIL
    -0.75
    ItemThumbnailImage
    -0.74
    PsyNetMessage
    -0.72
     conclud
    -0.69
    vation
    -0.67
    Cour
    -0.67
    HCR
    -0.67
     Geographic
    -0.65
    NetMessage
    -0.65
     predec
    -0.64
    POSITIVE LOGITS
    holes
    1.11
    hole
    1.02
    lord
    0.93
    fuck
    0.87
    nuts
    0.85
    buster
    0.85
    wit
    0.84
    bags
    0.84
    loads
    0.83
    lords
    0.81
    Act Density 0.022%

    No Known Activations