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

    Neuronpedia

    INDEX
    Explanations

    brackets and their contents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    edly
    -0.57
    ities
    -0.54
     CascadeType
    -0.54
     irregular
    -0.52
    endpush
    -0.52
    createCanvas
    -0.52
     preference
    -0.51
    paque
    -0.51
     Irregular
    -0.50
    globalData
    -0.50
    POSITIVE LOGITS
    出版年
    0.81
     autorytatywna
    0.77
     الرياضيه
    0.70
     للاسماء
    0.66
     للمعارف
    0.65
    UnusedPrivate
    0.61
    Aholisi
    0.60
    RegressionTest
    0.59
     ISNI
    0.59
    AsUp
    0.58
    Act Density 0.008%

    No Known Activations