INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     alguns
    0.33
     mniej
    0.32
     undesired
    0.32
     fewer
    0.32
     insuf
    0.32
     algunos
    0.31
     nějak
    0.31
     ovoj
    0.31
     estar
    0.31
     eventuali
    0.31
    POSITIVE LOGITS
     comprehensive
    0.42
    rizona
    0.37
     plethora
    0.36
     symphony
    0.36
     انتہائی
    0.35
     medley
    0.35
    romatic
    0.34
    uckland
    0.34
     multitude
    0.34
     panoramic
    0.34
    Act Density 0.258%

    No Known Activations