INDEX
    Explanations

    following sequences of events

    New Auto-Interp
    Negative Logits
     именно
    0.78
    ัญลักษณ์
    0.73
    0.72
    তেই
    0.69
    ේශ
    0.68
     بلکه
    0.68
     არა
    0.65
    実際に
    0.64
    נים
    0.64
     شائع
    0.63
    POSITIVE LOGITS
     follow
    2.33
     Follow
    2.16
    follow
    2.10
    Follow
    2.09
     ebenfalls
    2.06
     followup
    2.05
     follows
    2.04
     likewise
    1.94
     followed
    1.94
     FOLLOW
    1.79
    Act Density 0.121%

    No Known Activations