INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    С
    1.19
    ك
    1.14
    1.14
    Т
    1.14
    1.10
    الس
    1.06
    1.03
    1.00
    Д
    0.93
    0.93
    POSITIVE LOGITS
    art
    0.87
    0.80
     Supreme
    0.79
     _)
    0.79
    )
    0.79
    0.77
    atan
    0.77
    <0xB0>
    0.75
    '].
    0.74
     be
    0.74
    Act Density 0.008%

    No Known Activations