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

    Neuronpedia

    INDEX
    Explanations

    phrases related to user rights and content moderation policies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.82
    出版年
    -0.72
    الحياه
    -0.71
     perſon
    -0.69
     Efq
    -0.69
     "..\..\..\
    -0.69
    KommentareTeilen
    -0.68
    تقاوى
    -0.68
     незавершена
    -0.68
     ſta
    -0.68
    POSITIVE LOGITS
     arbitrarily
    0.49
     arbitrary
    0.46
     for
    0.43
     ${\
    0.42
     Future
    0.42
     per
    0.41
     simplemente
    0.41
    zer
    0.41
     باخ
    0.41
    цыі
    0.41
    Act Density 0.012%

    No Known Activations