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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical or statistical transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.71
    .
    -0.68
     
    -0.67
    ?
    -0.66
    ,
    -0.66
    ↵↵
    -0.66
    _
    -0.62
    (
    -0.60
    <eos>
    -0.60
     "
    -0.59
    POSITIVE LOGITS
    Билгалдахарш
    1.29
     propOrder
    1.29
    دانشنامهٔ
    1.28
     Efq
    1.21
    RenderAtEndOf
    1.20
     itſelf
    1.19
    存于互联网档案馆
    1.18
     BoxDecoration
    1.15
     nahilalakip
    1.15
     الحره
    1.15
    Act Density 0.482%

    No Known Activations