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

    Neuronpedia

    INDEX
    Explanations

    URLs and file paths associated with CGI scripts and binary data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    //:
    -0.61
     Bier
    -0.56
    UpInside
    -0.55
     dismissed
    -0.52
     pareti
    -0.52
    epik
    -0.52
     a
    -0.51
    sek
    -0.50
     contenir
    -0.50
    ことができる
    -0.50
    POSITIVE LOGITS
    cgi
    2.02
     cgi
    1.55
    CGI
    1.10
    __":
    1.09
     CGI
    1.04
     ModelExpression
    0.99
     ་་
    0.91
     miſ
    0.89
     myſelf
    0.89
     itſelf
    0.88
    Act Density 0.002%

    No Known Activations