INDEX
    Explanations

    instances of organized activism and community events

    New Auto-Interp
    Negative Logits
    DebugEnabled
    -0.16
     hâl
    -0.14
    echn
    -0.14
    hausen
    -0.14
    ONSE
    -0.14
    oeff
    -0.14
    VILLE
    -0.13
    owski
    -0.13
    .wp
    -0.13
     Yıl
    -0.13
    POSITIVE LOGITS
     anti
    0.15
    Textbox
    0.15
    gend
    0.15
    zell
    0.15
    rimp
    0.14
    strand
    0.14
     protest
    0.14
    090
    0.14
     supportive
    0.14
    çīĮ
    0.14
    Act Density 0.141%

    No Known Activations