INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     bona
    -0.08
     Roche
    -0.08
     overt
    -0.08
     Hor
    -0.08
     intens
    -0.08
     valmist
    -0.08
     груд
    -0.08
     Euro
    -0.08
     Quartet
    -0.07
     progn
    -0.07
    POSITIVE LOGITS
     shortening
    0.12
    0.10
     personnalis
    0.09
     shorten
    0.09
     shorter
    0.09
     chic
    0.09
     Indie
    0.09
     shortened
    0.09
    ugc
    0.09
    0.08
    Act Density 0.002%

    No Known Activations