INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    interesting
    -0.09
    Knowing
    -0.08
    тив
    -0.08
     conocida
    -0.08
     понрав
    -0.08
    known
    -0.08
    -0.08
     kennen
    -0.08
    интерес
    -0.08
     controleren
    -0.08
    POSITIVE LOGITS
    0.09
     đạt
    0.08
     prestige
    0.08
    0.07
     의원
    0.07
     linkage
    0.07
     votes
    0.07
     toch
    0.07
     esteem
    0.07
    0.07
    Act Density 0.000%

    No Known Activations