INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     hareket
    -0.09
     sails
    -0.08
    ía
    -0.08
     negó
    -0.08
    Charts
    -0.07
    观察
    -0.07
     observado
    -0.07
     dud
    -0.07
     simplic
    -0.07
     observes
    -0.07
    POSITIVE LOGITS
     automatisch
    0.08
    .Seek
    0.08
     Boden
    0.08
    [,
    0.08
     endings
    0.08
     Ending
    0.07
    0.07
    .Suppress
    0.07
    מעות
    0.07
     ziekte
    0.07
    Act Density 0.001%

    No Known Activations