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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or interactions between actors and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    certainly
    -0.55
     soulign
    -0.52
     indépend
    -0.50
     ciddi
    -0.48
     имеют
    -0.47
     montrent
    -0.46
     certainly
    -0.46
     ugy
    -0.46
     sérieux
    -0.45
     élevées
    -0.45
    POSITIVE LOGITS
    SharedDtor
    1.01
    évaluateur
    0.75
    djangoproject
    0.71
     CURIAM
    0.70
     nahilalakip
    0.70
     snippetHide
    0.69
     يتيمه
    0.69
     ویکی‌پدیا
    0.68
    richTextPanel
    0.67
    InputBorder
    0.67
    Act Density 0.112%

    No Known Activations