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

    Neuronpedia

    INDEX
    Explanations

    question marks and exclamation points in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.83
    $
    -0.73
     AspNetCore
    -0.68
     Ample
    -0.65
     mesure
    -0.60
    Personendaten
    -0.57
    dafx
    -0.57
    .}\
    -0.56
    fahan
    -0.56
     Tortoise
    -0.55
    POSITIVE LOGITS
    !!!!!!!!!!!!!!!!
    0.60
    !!!!!!!!
    0.56
    *~*~
    0.51
    וך
    0.51
    urlpatterns
    0.50
    曜
    0.49
     Seb
    0.49
    ώ
    0.48
    caud
    0.47
    MethodManager
    0.47
    Act Density 0.425%

    No Known Activations