INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     polluted
    -0.09
    コピー
    -0.08
     pollution
    -0.08
     jasmine
    -0.08
    pras
    -0.08
    -0.08
     Expected
    -0.08
     Painted
    -0.07
    ดาว
    -0.07
     Qu
    -0.07
    POSITIVE LOGITS
     BDSM
    0.16
     bondage
    0.12
     oppression
    0.10
    იმ
    0.09
    িম
    0.09
     erotic
    0.09
    0.09
    ಿಮೆ
    0.09
    िम
    0.08
     torture
    0.08
    Act Density 0.010%

    No Known Activations