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

    Neuronpedia

    INDEX
    Explanations

    high-frequency occurrences of punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ลำ
    -0.57
    ódó
    -0.56
    떻
    -0.50
    UpDown
    -0.48
     arbo
    -0.47
    ljeno
    -0.46
    Gr
    -0.43
     ок
    -0.43
     Loving
    -0.43
    anskje
    -0.43
    POSITIVE LOGITS
     &___
    0.87
    )";
    0.86
    Numerology
    0.81
    ViewImports
    0.81
     unknownFields
    0.79
    ExtendWith
    0.78
    $_['
    0.77
    <bos>
    0.77
    EndContext
    0.75
    )");
    0.75
    Act Density 0.581%

    No Known Activations