INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     feud
    -0.08
     Stoke
    -0.08
     Sinn
    -0.08
    (alias
    -0.08
     fiscal
    -0.08
     vague
    -0.08
     Chapman
    -0.07
     legislation
    -0.07
     Sith
    -0.07
    ugo
    -0.07
    POSITIVE LOGITS
     얼굴
    0.14
     Facial
    0.13
    0.13
     चेहरे
    0.11
     detects
    0.11
    etected
    0.11
     dete
    0.10
     detected
    0.10
    Contours
    0.10
     facial
    0.10
    Act Density 0.008%

    No Known Activations