INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.69
     المعيارى
    -0.68
     kasarigan
    -0.60
     otomatig
    -0.57
    Vidite
    -0.57
    хьтан
    -0.56
     transférez
    -0.54
    angliski
    -0.54
     незавершена
    -0.53
    verläs
    -0.53
    POSITIVE LOGITS
     face
    1.85
     Face
    1.74
    Face
    1.68
     FACE
    1.62
    face
    1.59
     faces
    1.58
    FACE
    1.43
     Faces
    1.41
     facial
    1.30
    Faces
    1.28
    Act Density 0.021%

    No Known Activations