INDEX
    Explanations

    references to dancing or dance-related activities

    New Auto-Interp
    Negative Logits
     gson
    -0.32
     Gunt
    -0.30
     Ruhe
    -0.28
     devrez
    -0.28
     unters
    -0.28
     "<?
    -0.27
    inguém
    -0.27
    -0.27
     answers
    -0.27
     deverá
    -0.27
    POSITIVE LOGITS
     dancing
    1.20
     danced
    1.09
    dancing
    1.06
     dance
    1.04
     Dancing
    1.01
    Dancing
    1.00
     dances
    0.97
     DANCE
    0.96
    Dance
    0.91
     Dance
    0.91
    Act Density 0.020%

    No Known Activations