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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing user benefit and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.50
    CloseOperation
    -0.50
    vább
    -0.47
    NamedQuery
    -0.41
     مشارکت‌کنندگان
    -0.40
    InjectAttribute
    -0.37
     consentimento
    -0.36
     оригіналу
    -0.35
     ExecuteAsync
    -0.35
     extranjeros
    -0.35
    POSITIVE LOGITS
     CURIAM
    0.55
     YORK
    0.55
     Italijani
    0.55
    York
    0.47
    躇
    0.47
    Вам
    0.47
     York
    0.45
     мной
    0.45
    TestTools
    0.45
    ceğim
    0.44
    Act Density 0.244%

    No Known Activations