INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ctomy
    -0.09
     które
    -0.08
     destabil
    -0.08
     synonyms
    -0.08
     gefähr
    -0.08
    conce
    -0.08
     densely
    -0.08
     teadm
    -0.08
     spes
    -0.07
     Satan
    -0.07
    POSITIVE LOGITS
     faire
    0.09
     fairness
    0.09
     fashion
    0.08
     FIFO
    0.08
     очеред
    0.08
     Ф
    0.08
    0.08
    0.08
     toegepast
    0.08
     fifo
    0.08
    Act Density 0.003%

    No Known Activations