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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to statistics or scores

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ?
    -0.48
    Cy
    -0.47
    лежа
    -0.47
     letz
    -0.47
    BitSet
    -0.47
     institution
    -0.46
     Markham
    -0.46
    (
    -0.46
    ({
    -0.45
    sts
    -0.44
    POSITIVE LOGITS
     للاسماء
    0.89
     وتسجيلات
    0.81
    Autoritní
    0.79
    makeText
    0.77
    LookAnd
    0.75
    TagMode
    0.75
     ویکی‌پدی
    0.69
     Roskov
    0.69
     typelib
    0.67
    __":
    0.67
    Act Density 0.002%

    No Known Activations