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

    Neuronpedia

    INDEX
    Explanations

    references to the previous year and comparisons to past performance or characteristics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    middels
    -0.56
    '};
    -0.53
    >*/
    -0.53
    erweise
    -0.49
    )");
    -0.49
     Administrativna
    -0.47
    );*/
    -0.47
     ")");
    -0.46
    //
    -0.46
     %@",
    -0.45
    POSITIVE LOGITS
    Previous
    0.68
    previous
    0.67
     Previous
    0.66
     previous
    0.63
     PREVIOUS
    0.59
     smtplib
    0.59
    ancienne
    0.58
    ActionCreators
    0.58
    上一
    0.57
    oneofs
    0.57
    Act Density 0.150%

    No Known Activations