INDEX
    Explanations

    issues related to social justice and systemic inequalities

    New Auto-Interp
    Negative Logits
    sel
    -0.18
    eature
    -0.16
    upo
    -0.15
    à¹ĩà¸ķาม
    -0.15
    uet
    -0.15
    peon
    -0.14
    ãģ«ãĤĤ
    -0.14
    gn
    -0.14
    noch
    -0.14
    ieg
    -0.14
    POSITIVE LOGITS
     totiž
    0.17
    eras
    0.15
    ãģ¾ãģļ
    0.14
    949
    0.14
    765
    0.14
    à¸Ĺะ
    0.14
     Tome
    0.14
    616
    0.14
     Rev
    0.14
     Sun
    0.13
    Act Density 1.334%

    No Known Activations