INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     in
    -0.93
     order
    -0.61
     on
    -0.59
     with
    -0.54
     was
    -0.53
     to
    -0.52
     and
    -0.51
     as
    -0.51
     regarding
    -0.50
     for
    -0.49
    POSITIVE LOGITS
    <bos>
    1.18
     démocr
    1.05
    AndEndTag
    1.03
    windowFixed
    1.02
    Personensuche
    0.96
     propOrder
    0.96
     réguli
    0.94
     мәкал
    0.94
     définiti
    0.94
     AssemblyCulture
    0.94
    Act Density 0.039%

    No Known Activations