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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Exacts
    -0.68
    OrNil
    -0.66
    __":
    -0.66
     autorytatywna
    -0.65
    __':
    -0.65
    ArrowToggle
    -0.65
    UnknownFields
    -0.62
    mybatisplus
    -0.61
    uxxxx
    -0.60
    __':
    -0.60
    POSITIVE LOGITS
    DoubleQuotes
    0.56
     يتيمه
    0.52
    azon
    0.48
    anti
    0.46
    lev
    0.45
    αλ
    0.43
     ***!
    0.42
    zik
    0.41
    ніципа
    0.41
     Weil
    0.41
    Act Density 0.018%

    No Known Activations