INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    'll
    -0.09
     BTS
    -0.07
     MER
    -0.07
     thermo
    -0.07
     boutique
    -0.07
    Sp
    -0.07
     über
    -0.07
    _AD
    -0.07
     neka
    -0.07
    biz
    -0.07
    POSITIVE LOGITS
     poucos
    0.09
     대부분
    0.09
     सारे
    0.09
     rares
    0.08
    Except
    0.08
     einzige
    0.08
     few
    0.08
    0.08
     edema
    0.08
     অক
    0.08
    Act Density 0.012%

    No Known Activations