INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Unclassified
    -0.84
    alerie
    -0.82
    aniline
    -0.81
    -0.80
    ługa
    -0.77
    críbete
    -0.77
    原标题
    -0.76
     ficción
    -0.76
    lasyon
    -0.75
    طاء
    -0.74
    POSITIVE LOGITS
     exile
    4.06
     exiled
    3.16
     exiles
    2.59
     Exile
    2.53
     banished
    1.61
     expatri
    1.57
     banish
    1.45
     sür
    1.23
     asylum
    1.15
     diaspora
    1.14
    Act Density 0.040%

    No Known Activations