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

    Neuronpedia

    INDEX
    Explanations

    parentheses used for content pairs or grouping in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.85
    CloseOperation
    -0.79
    ](#
    -0.78
    -0.75
     ویکی‌پدیای
    -0.73
     Ảnh
    -0.72
    MessageState
    -0.69
    labus
    -0.69
    SBATCH
    -0.69
     Rasul
    -0.68
    POSITIVE LOGITS
    L
    0.54
     L
    0.52
     Fen
    0.49
     
    0.48
    C
    0.48
    import
    0.47
    “
    0.47
    界
    0.47
    </em>
    0.46
    com
    0.46
    Act Density 0.023%

    No Known Activations