INDEX
    Explanations

    academic authorship

    New Auto-Interp
    Negative Logits
    .sprite
    -0.09
    sprite
    -0.08
     mildew
    -0.08
    otherapy
    -0.08
     Theater
    -0.08
     Tween
    -0.08
     suitcase
    -0.07
    _Pl
    -0.07
     theater
    -0.07
    Sprite
    -0.07
    POSITIVE LOGITS
     affiliations
    0.14
     authors
    0.13
    Authors
    0.13
     collaborators
    0.12
    作者
    0.12
     colaboradores
    0.12
     autoria
    0.12
     affiliation
    0.11
     Authors
    0.11
     auteurs
    0.11
    Act Density 0.052%

    No Known Activations