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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific tokens or labels indicating the start of a new sequence or section in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.86
    SharedDtor
    -0.80
     autorytatywna
    -0.79
     saites
    -0.79
     للمعارف
    -0.72
     esternos
    -0.72
    ^(@
    -0.72
     kaarangay
    -0.71
    ništvo
    -0.71
     المعيارى
    -0.71
    POSITIVE LOGITS
    isNaN
    0.65
     PyLong
    0.62
     numbers
    0.60
    NSNumber
    0.59
    数字
    0.58
     数字
    0.56
     numeric
    0.55
    zahlen
    0.54
     number
    0.53
     angka
    0.53
    Act Density 0.750%

    No Known Activations