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

    Neuronpedia

    INDEX
    Explanations

    substantial variations in unique identifiers related to document subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ainfi
    -0.63
     ejus
    -0.60
     quæ
    -0.59
     发表于
    -0.58
    الدراسه
    -0.55
     malheureux
    -0.54
     Ibidem
    -0.53
    forRoot
    -0.53
     auffi
    -0.53
     aveug
    -0.53
    POSITIVE LOGITS
     للمعارف
    0.82
    &-
    0.71
     незавершена
    0.66
    ')['
    0.60
    */].
    0.60
    ().__
    0.57
    doPost
    0.57
    PreferredItem
    0.57
    }_\
    0.57
    GeneratedCode
    0.56
    Act Density 0.453%

    No Known Activations