INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     místo
    -0.07
     Craft
    -0.06
         
    -0.06
     Andrea
    -0.06
     cum
    -0.06
     scrape
    -0.06
     shark
    -0.06
     verify
    -0.06
     fabricated
    -0.06
     exposition
    -0.06
    POSITIVE LOGITS
     Own
    0.08
     own
    0.07
    Own
    0.07
    .toLocale
    0.07
     ownership
    0.06
    .XtraEditors
    0.06
    _ipv
    0.06
    .BackgroundImageLayout
    0.06
     Olivier
    0.06
    -dir
    0.06
    Act Density 0.005%

    No Known Activations