INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     spanking
    -0.07
     semanas
    -0.07
     panties
    -0.07
     Beled
    -0.07
     bacterial
    -0.06
    -0.06
    -0.06
     killings
    -0.06
     nine
    -0.06
     Prosec
    -0.06
    POSITIVE LOGITS
    /oct
    0.07
     descricao
    0.07
     waterproof
    0.07
    いや
    0.07
    DF
    0.07
     dislikes
    0.06
    ColumnInfo
    0.06
     GENERAL
    0.06
     puts
    0.06
    _descriptor
    0.06
    Act Density 0.293%

    No Known Activations