INDEX
    Explanations

    references to activism and social justice movements

    New Auto-Interp
    Negative Logits
    urch
    -0.17
    aine
    -0.14
     Neville
    -0.14
    ura
    -0.14
    aticon
    -0.14
    å¨ľ
    -0.14
    avar
    -0.13
    olean
    -0.13
    alin
    -0.13
    uben
    -0.13
    POSITIVE LOGITS
    .nlm
    0.16
    nothrow
    0.15
     Ekon
    0.14
    ekk
    0.14
    storybook
    0.14
     oh
    0.14
    енÑĥ
    0.14
     Gü
    0.14
     "-//
    0.13
    kening
    0.13
    Act Density 0.100%

    No Known Activations