INDEX
    Explanations

    words or fragments of words that relate to entertainment or arts

    New Auto-Interp
    Negative Logits
     addCriterion
    -0.19
    legg
    -0.16
    ondo
    -0.16
    ãĥ³ãĤ¬
    -0.16
    tega
    -0.15
    rat
    -0.15
    andel
    -0.15
    okers
    -0.15
    ddit
    -0.14
    @student
    -0.14
    POSITIVE LOGITS
     Rules
    0.16
    -serif
    0.15
     dressing
    0.15
     Rule
    0.15
    ITCH
    0.14
    ëĵ±
    0.14
    brook
    0.14
     infl
    0.14
     Gallup
    0.14
     Bron
    0.14
    Act Density 0.000%

    No Known Activations