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

    Neuronpedia

    INDEX
    Explanations

    references to controversies involving celebrities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Caleb
    -0.16
    AFX
    -0.15
    NK
    -0.15
    IFn
    -0.14
    xcb
    -0.14
     Ariel
    -0.14
    erture
    -0.14
    ç´Ļ
    -0.14
    лини
    -0.13
     vamp
    -0.13
    POSITIVE LOGITS
     Cosby
    0.52
    Cos
    0.38
    .Cos
    0.36
     COS
    0.35
    cos
    0.34
     Cos
    0.33
     cos
    0.30
    (cos
    0.29
     Bill
    0.29
    _cos
    0.28
    Act Density 0.003%

    No Known Activations