INDEX
    Explanations

    references to political threats and violence against intellectuals

    New Auto-Interp
    Negative Logits
    omu
    -0.15
     worldwide
    -0.14
    omit
    -0.14
     Fres
    -0.14
     Apt
    -0.14
     &
    -0.14
    šek
    -0.13
     apt
    -0.13
     pitch
    -0.13
     SUBSTITUTE
    -0.13
    POSITIVE LOGITS
     Gram
    0.16
    :animated
    0.15
     Gand
    0.15
    ofile
    0.14
    pus
    0.14
    :UIAlert
    0.14
     FLAC
    0.14
     addCriterion
    0.14
    RIES
    0.14
    dal
    0.14
    Act Density 0.036%

    No Known Activations