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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ul
    1.49
    し
    1.49
    า
    1.46
    س
    1.36
    ל
    1.27
    ות
    1.27
    un
    1.23
    ס
    1.18
    :
    1.16
    น
    1.08
    POSITIVE LOGITS
    ت
    0.92
     that
    0.90
    {,}
    0.87
    IAN
    0.86
    <unused2197>
    0.86
    一
    0.84
    AT
    0.82
    {
    0.82
    0.82
    логи
    0.80
    Act Density 0.000%

    No Known Activations