INDEX
    Explanations

    references to performance and entertainment-related acts

    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.63
    DockStyle
    -0.61
    FieldBuilder
    -0.53
    öße
    -0.53
    SPJ
    -0.53
    geordneten
    -0.52
    setVerticalGroup
    -0.52
    álise
    -0.51
    twimg
    -0.50
    Guía
    -0.49
    POSITIVE LOGITS
     circus
    1.11
     Circus
    0.99
     juggling
    0.96
     Cirque
    0.94
     magician
    0.94
     magicians
    0.94
     acrobat
    0.92
    circus
    0.91
     acrob
    0.90
     cirque
    0.88
    Act Density 0.188%

    No Known Activations