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

    Neuronpedia

    INDEX
    Explanations

    specific formatting elements (like punctuation and special characters) in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.68
    GEBURTSDATUM
    -0.65
     estekak
    -0.65
    PhysRev
    -0.63
    formik
    -0.63
     BoxFit
    -0.61
    UnusedPrivate
    -0.61
    PerformLayout
    -0.60
     SqlParameter
    -0.60
     ویکی‌پدیا
    -0.60
    POSITIVE LOGITS
    いずれ
    0.94
    どちらも
    0.82
    どれも
    0.72
     Both
    0.69
    both
    0.69
    Both
    0.69
    どちら
    0.67
    それぞれ
    0.66
     both
    0.65
    両方
    0.64
    Act Density 0.390%

    No Known Activations