INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Kuchen
    -0.08
    ichtigen
    -0.08
     cloves
    -0.08
    ='../
    -0.08
    (limit
    -0.08
     ain't
    -0.08
     cant
    -0.08
    -operated
    -0.08
    以上
    -0.07
    geleverd
    -0.07
    POSITIVE LOGITS
    negative
    0.08
     negative
    0.08
    tax
    0.08
    Tax
    0.07
     negatieve
    0.07
     Taxes
    0.07
    Negative
    0.07
     taxing
    0.07
     Tax
    0.07
     tagging
    0.07
    Act Density 0.000%

    No Known Activations