INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    screw
    0.51
    0.43
    ठमा
    0.39
     screw
    0.39
    Screw
    0.39
    ंगामा
    0.38
    зив
    0.37
    roar
    0.37
     rahu
    0.36
     গান্ধী
    0.36
    POSITIVE LOGITS
     highlighting
    1.47
    Highlight
    1.32
    highlight
    1.30
     highlight
    1.30
     Highlight
    1.27
     highlighted
    1.20
     highlighter
    1.19
     highlights
    1.13
    highlights
    1.03
     Highlights
    1.00
    Act Density 0.017%

    No Known Activations