INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     حوصل
    0.38
    ිරීම
    0.38
    дут
    0.38
    0.37
    ոտ
    0.35
    ர்ம
    0.34
    vdash
    0.33
     }=
    0.33
    0.33
    0.33
    POSITIVE LOGITS
     thank
    4.09
     Thank
    3.83
    Thank
    3.80
    thank
    3.56
     THANK
    3.42
    谢谢
    3.25
     thanked
    3.23
    THANK
    3.23
     Thanks
    3.19
     thanking
    3.17
    Act Density 0.121%

    No Known Activations