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

    Neuronpedia

    INDEX
    Explanations

    structured data or programming constructs related to categories and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ...
    -0.52
    $
    -0.42
     mé
    -0.39
    ere
    -0.38
     die
    -0.38
     stand
    -0.38
     an
    -0.38
     total
    -0.38
    кло
    -0.36
    beza
    -0.35
    POSITIVE LOGITS
    Personendaten
    1.06
     صوتيه
    0.95
    PerformLayout
    0.94
     незавершена
    0.92
    GEBURTSDATUM
    0.91
     ویکی‌پدیا
    0.85
     ویکی‌پدیای
    0.85
    ագրություններ
    0.84
     Normdatei
    0.84
     للاسماء
    0.81
    Act Density 2.126%

    No Known Activations