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

    Neuronpedia

    INDEX
    Explanations

    references to formal assumptions, definitions, and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lenker
    -0.68
    رشف
    -0.64
    sidemargin
    -0.62
    HasForeignKey
    -0.61
     compositeur
    -0.60
     ++)
    -0.58
     Majefty
    -0.58
    PreferredItem
    -0.57
     autorytatywna
    -0.56
    Ссылки
    -0.56
    POSITIVE LOGITS
    الحياه
    0.68
    帖最后由
    0.47
     Eink
    0.47
    WEBPACK
    0.47
    bular
    0.45
     participantes
    0.44
    uruhan
    0.43
     javax
    0.42
    modern
    0.41
    躇
    0.41
    Act Density 1.151%

    No Known Activations