INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     illustration
    -0.10
    With
    -0.08
     illustrations
    -0.08
     Illustration
    -0.08
    _with
    -0.08
     langt
    -0.08
     illustrated
    -0.07
     invites
    -0.07
    Analyse
    -0.07
     illustrate
    -0.07
    POSITIVE LOGITS
     lectus
    0.08
     foly
    0.08
     päät
    0.08
    YES
    0.08
     rpt
    0.08
    stek
    0.08
     atender
    0.08
     YES
    0.07
     погод
    0.07
    Rpt
    0.07
    Act Density 0.007%

    No Known Activations