INDEX
    Explanations

    references to military ranks and organizations

    New Auto-Interp
    Negative Logits
    issen
    -0.16
    itel
    -0.15
    _ONCE
    -0.15
    ullets
    -0.15
    logg
    -0.15
    ihanna
    -0.15
    elsen
    -0.15
    pta
    -0.14
    marvin
    -0.14
    esch
    -0.14
    POSITIVE LOGITS
     reserves
    0.17
    å°¼äºļ
    0.17
     Volunteers
    0.15
    kor
    0.15
     reserve
    0.15
     Regular
    0.15
     regs
    0.14
    åĭŁ
    0.14
     Boys
    0.14
     reserva
    0.14
    Act Density 0.098%

    No Known Activations