INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    0.90
    0.87
     ی
    0.77
     ܠ
    0.77
    ۔
    0.75
    0.73
    𝔂
    0.73
    0.72
    0.72
    یکا
    0.71
    POSITIVE LOGITS
    n
    1.09
    in
    0.98
    <0x0D>
    0.82
    et
    0.80
    s
    0.80
    де
    0.80
    is
    0.79
    ell
    0.79
    re
    0.77
    en
    0.77
    Act Density 0.002%

    No Known Activations