INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     apenas
    0.45
     שלך
    0.42
     reactivity
    0.41
    extremely
    0.40
     dvě
    0.40
     മാത്ര
    0.39
     resultante
    0.39
    Two
    0.39
    ératures
    0.39
    ਤਰ
    0.39
    POSITIVE LOGITS
     repetir
    0.70
    Repeat
    0.67
     Repeating
    0.63
    Repeating
    0.62
     repeats
    0.61
     ripet
    0.60
     motifs
    0.59
    繰り返
    0.57
     Repeat
    0.56
    一遍
    0.56
    Act Density 0.019%

    No Known Activations