INDEX
    Explanations

    references to nonviolent movements and figures associated with civil disobedience

    New Auto-Interp
    Negative Logits
    à¸Ĺร
    -0.15
     Prospect
    -0.15
     prospect
    -0.14
    Äįe
    -0.14
    /tasks
    -0.14
    ULATOR
    -0.14
    oÅĻ
    -0.14
     Alman
    -0.13
    ej
    -0.13
    UILTIN
    -0.13
    POSITIVE LOGITS
    uchos
    0.15
    enz
    0.15
     Gros
    0.14
    asco
    0.14
    vect
    0.14
    \grid
    0.14
    307
    0.13
    leaf
    0.13
    ivas
    0.13
    ronic
    0.13
    Act Density 0.011%

    No Known Activations