INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Reid
    -0.08
     Geoffrey
    -0.07
     Pegasus
    -0.07
     outright
    -0.07
     ack
    -0.07
     wond
    -0.07
     imperial
    -0.07
     acol
    -0.07
     antic
    -0.07
    udir
    -0.07
    POSITIVE LOGITS
     Vorstand
    0.08
     mocked
    0.08
     beraber
    0.08
     nem
    0.07
     partisan
    0.07
    RT
    0.07
    BH
    0.07
     Portfolio
    0.07
     tart
    0.07
     sát
    0.07
    Act Density 0.000%

    No Known Activations