INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     kip
    -0.08
     specializes
    -0.08
     sembl
    -0.08
     realm
    -0.08
     tör
    -0.07
     specialize
    -0.07
    -inspired
    -0.07
    [right
    -0.07
     peuple
    -0.07
     until
    -0.07
    POSITIVE LOGITS
    stell
    0.10
    FROM
    0.08
     realizada
    0.08
     жаса
    0.08
    dream
    0.08
     multa
    0.07
     fija
    0.07
    stellen
    0.07
     완료
    0.07
    .FC
    0.07
    Act Density 0.008%

    No Known Activations