INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    inim
    0.67
     spins
    0.66
     frugal
    0.66
     Kazim
    0.64
     curls
    0.64
     monocytes
    0.64
     mond
    0.63
     বাজেট
    0.61
    0.61
     حکمت
    0.61
    POSITIVE LOGITS
     sexual
    2.33
     rape
    2.03
     Sexual
    2.01
    Sexual
    1.98
     Rape
    1.90
     SEXUAL
    1.83
    sexual
    1.80
     sexually
    1.75
    rape
    1.72
     raped
    1.63
    Act Density 0.429%

    No Known Activations