INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     yummy
    0.71
     smart
    0.71
     smartest
    0.71
     mooie
    0.70
     smarter
    0.70
     savvy
    0.68
     nifty
    0.62
     poderoso
    0.62
     HUGE
    0.60
    เยอะ
    0.60
    POSITIVE LOGITS
     undesirable
    0.87
     unsuitable
    0.80
     unacceptable
    0.78
     objectionable
    0.77
     unfavorable
    0.75
     alarming
    0.75
     disagreeable
    0.75
     inappropriate
    0.75
     anomalous
    0.74
     detrimental
    0.73
    Act Density 1.316%

    No Known Activations