INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    vanished
    -0.07
     projektu
    -0.06
     законом
    -0.06
     moisture
    -0.06
    Metric
    -0.06
     reactions
    -0.06
     Styles
    -0.06
    -0.06
     aest
    -0.06
     houses
    -0.06
    POSITIVE LOGITS
     spanking
    0.35
    .BigDecimal
    0.08
    .Field
    0.07
    .signature
    0.07
     Sitting
    0.07
     handful
    0.07
     complications
    0.06
    писание
    0.06
     Angola
    0.06
    รงเร
    0.06
    Act Density 0.001%

    No Known Activations