INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    әрмәләр
    -0.68
    Diweddarwch
    -0.55
     arşivlendi
    -0.54
    Искәрмәләр
    -0.53
    ArgumentParser
    -0.52
    ">//
    -0.52
    hbs
    -0.52
     betweenstory
    -0.52
    UserScript
    -0.49
     оригіналу
    -0.49
    POSITIVE LOGITS
     age
    0.76
     âge
    0.61
    âge
    0.57
     usia
    0.53
     edad
    0.53
    Age
    0.52
     Age
    0.52
     plegable
    0.52
     AGE
    0.52
    age
    0.51
    Act Density 0.001%

    No Known Activations