INDEX
    Explanations

    phrases related to social justice and racial issues

    New Auto-Interp
    Negative Logits
    riel
    -0.15
     Intercept
    -0.15
     activity
    -0.14
    ç¿°
    -0.14
     Thrones
    -0.13
     Macron
    -0.13
     continents
    -0.13
    .addRow
    -0.13
     HomeController
    -0.13
     feet
    -0.13
    POSITIVE LOGITS
     breed
    0.22
     normal
    0.17
     era
    0.17
     Breed
    0.16
     guard
    0.16
    erais
    0.15
    -era
    0.15
    -normal
    0.14
     generation
    0.14
     wave
    0.14
    Act Density 0.089%

    No Known Activations