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

    Neuronpedia

    INDEX
    Explanations

    words in Arabic or phrases that relate to preference and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NDEBUG
    -0.62
     officiels
    -0.59
     nationaux
    -0.58
    лії
    -0.56
     religieuses
    -0.55
     sauvages
    -0.53
     DELLE
    -0.53
     humaines
    -0.50
     militaires
    -0.50
    сії
    -0.49
    POSITIVE LOGITS
     חיצוניים
    0.65
    principalColumn
    0.63
     مرئيه
    0.63
     ujednoznacz
    0.60
    InputBorder
    0.59
     يتيمه
    0.58
     disambiguazione
    0.58
     وتسجيلات
    0.55
     HasFactory
    0.54
    
    0.53
    Act Density 0.026%

    No Known Activations