INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    saraba
    -0.59
    OCCURRED
    -0.55
    beur
    -0.52
     سكانية
    -0.51
    >>;
    -0.49
    }>;
    -0.49
    LookAnd
    -0.48
    jot
    -0.48
    ftance
    -0.47
    ӗ
    -0.47
    POSITIVE LOGITS
    www
    4.17
     www
    3.36
    Www
    2.46
    WWW
    2.43
     WWW
    2.04
    wwww
    1.98
    wwwww
    1.59
    ww
    1.45
    http
    1.38
     http
    1.34
    Act Density 0.050%

    No Known Activations