INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Participating
    0.44
     সংখ্যাগ
    0.37
     nying
    0.36
    เหล่า
    0.36
     femenino
    0.36
     whichever
    0.35
     Otras
    0.35
     âg
    0.34
     Nós
    0.33
    சிக்கும்
    0.33
    POSITIVE LOGITS
     человек
    2.23
     people
    2.11
     person
    2.03
     personnes
    1.88
     someone
    1.86
     사람이
    1.85
     люди
    1.84
     personne
    1.83
     pessoa
    1.82
     человека
    1.81
    Act Density 0.035%

    No Known Activations