INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     first
    0.80
     første
    0.79
     충분
    0.77
     بالضبط
    0.75
    0.73
     adultery
    0.71
     only
    0.70
     majority
    0.69
     hence
    0.69
     ندارد
    0.68
    POSITIVE LOGITS
    Miscellaneous
    1.64
     miscellaneous
    1.62
     Miscellaneous
    1.59
    Other
    1.55
    Others
    1.53
    その他の
    1.49
    その他
    1.47
    อื่นๆ
    1.44
    Otros
    1.44
    others
    1.44
    Act Density 0.740%

    No Known Activations