INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     abrupt
    0.93
     brownish
    0.81
     blushing
    0.80
    myfaces
    0.76
     sensual
    0.76
     sudden
    0.75
    0.74
     compensating
    0.74
     sexy
    0.73
     creamy
    0.73
    POSITIVE LOGITS
    Wear
    0.85
    ring
    0.84
    forma
    0.80
    lingu
    0.80
    baru
    0.80
    meet
    0.80
    length
    0.80
    ripsi
    0.79
    rek
    0.77
    rir
    0.76
    Act Density 0.001%

    No Known Activations