INDEX
    Explanations

    references to performance and entertainment in relation to music or shows

    New Auto-Interp
    Negative Logits
    odb
    -0.16
    bris
    -0.15
     Votes
    -0.15
    aisal
    -0.15
    uppy
    -0.14
    oningen
    -0.14
     Sparks
    -0.14
    antity
    -0.14
    raya
    -0.14
    entiful
    -0.13
    POSITIVE LOGITS
     exc
    0.25
     delivered
    0.24
     impress
    0.24
     ace
    0.23
     deliver
    0.23
     delivery
    0.22
     delivering
    0.21
     dazz
    0.21
     ast
    0.20
     prove
    0.20
    Act Density 0.131%

    No Known Activations