INDEX
    Explanations

    references to celebrity involvement in social and political issues

    New Auto-Interp
    Negative Logits
    ingle
    -0.16
    aus
    -0.16
    uko
    -0.15
    ac
    -0.15
    wp
    -0.15
    emat
    -0.14
    venge
    -0.14
     Flores
    -0.14
    oen
    -0.14
    -cols
    -0.14
    POSITIVE LOGITS
    dsp
    0.16
    Spi
    0.15
     Estates
    0.15
     Zi
    0.15
    AndGet
    0.15
     doz
    0.14
    udad
    0.14
     ance
    0.14
    DSP
    0.14
     nÄĥ
    0.14
    Act Density 0.251%

    No Known Activations