INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     amelyet
    0.29
     осіб
    0.28
     অধ্যয়ন
    0.28
     utilisant
    0.27
     veuillez
    0.27
     utilizzando
    0.26
     permettant
    0.26
     Approximately
    0.26
     appartenant
    0.25
     actuellement
    0.25
    POSITIVE LOGITS
     things
    0.56
     someone
    0.52
     somebody
    0.52
     somehow
    0.48
    someone
    0.47
     something
    0.47
     whoever
    0.46
     everytime
    0.46
     THEY
    0.45
    things
    0.44
    Act Density 1.089%

    No Known Activations