INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     sabot
    0.49
     Gutenberg
    0.49
     poached
    0.45
     breakouts
    0.45
     девочки
    0.45
     Antarctica
    0.42
     cerevisiae
    0.42
    jeeling
    0.41
     steampunk
    0.41
     antioxid
    0.41
    POSITIVE LOGITS
     полицей
    1.13
     police
    1.09
    Police
    1.09
    police
    1.07
     policías
    1.07
     Police
    1.05
    警察
    1.05
     경찰
    1.02
     پولیس
    0.96
     policing
    0.95
    Act Density 0.100%

    No Known Activations