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

    Neuronpedia

    INDEX
    Explanations

    exclamations expressing frustration or confusion

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Joy
    -0.76
     Cosponsors
    -0.75
    Vert
    -0.74
    NetMessage
    -0.71
    %:
    -0.69
    ufact
    -0.69
    zes
    -0.68
    PsyNetMessage
    -0.67
    ause
    -0.67
    CI
    -0.65
    POSITIVE LOGITS
    hole
    0.81
    holes
    0.78
    ishly
    0.73
    urous
    0.72
    dump
    0.70
     damn
    0.67
    agna
    0.65
    fuck
    0.64
     grin
    0.63
     kidding
    0.63
    Act Density 0.022%

    No Known Activations