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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating names and identifications of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kaynağından
    -0.54
    lossenen
    -0.51
    ideration
    -0.49
    لیسی
    -0.49
    calar
    -0.48
    ModelSerializer
    -0.48
     patching
    -0.45
     trust
    -0.45
    apyrus
    -0.45
     Grayson
    -0.44
    POSITIVE LOGITS
    0.65
    CloseOperation
    0.62
    تقاوى
    0.61
    Formik
    0.60
    VIAF
    0.59
    enumi
    0.56
     ویکی‌پدیای
    0.56
    ншни
    0.56
     affectionately
    0.55
    Gemeinsame
    0.55
    Act Density 0.233%

    No Known Activations