INDEX
    Explanations

    movement direction / continuation

    New Auto-Interp
    Negative Logits
    0.37
     señalado
    0.36
     Ната
    0.35
     llamado
    0.35
    0.35
    0.35
    ελ
    0.34
     называ
    0.34
     preferências
    0.34
     appelé
    0.33
    POSITIVE LOGITS
     upto
    0.67
     advices
    0.61
     abit
    0.59
     thru
    0.59
     equipments
    0.57
     appart
    0.55
     atleast
    0.55
     unto
    0.54
     trough
    0.53
     ppl
    0.51
    Act Density 0.067%

    No Known Activations