INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Inspir
    -0.09
     inspir
    -0.08
     Loud
    -0.08
     brut
    -0.07
     Feel
    -0.07
    issions
    -0.07
     Inspiration
    -0.07
     Rich
    -0.07
    Inspir
    -0.07
     symmetry
    -0.07
    POSITIVE LOGITS
     permissible
    0.09
    (mail
    0.08
    rowser
    0.08
     billionaire
    0.08
     shareholder
    0.08
     очередь
    0.08
    ayaa
    0.08
    .Millisecond
    0.08
     возника
    0.08
     seguirá
    0.08
    Act Density 0.002%

    No Known Activations