INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     belanja
    -0.57
     On
    -0.50
     actionMode
    -0.49
    isNotBlank
    -0.48
     encontraban
    -0.48
    kirakan
    -0.48
     maintained
    -0.47
    maintained
    -0.47
    tumblr
    -0.46
     affirmé
    -0.46
    POSITIVE LOGITS
     Monfieur
    0.87
     purpoſe
    0.87
     Majefty
    0.84
     Diſ
    0.79
     ſmall
    0.79
     Anſ
    0.77
     ſtand
    0.77
     ſeveral
    0.76
     reaſon
    0.76
     preſent
    0.73
    Act Density 0.608%

    No Known Activations