INDEX
    Explanations

    terms related to segregation and its implications in society

    New Auto-Interp
    Negative Logits
    xn
    -0.16
    ly
    -0.15
     Prism
    -0.15
    398
    -0.15
    ippy
    -0.14
    asty
    -0.14
    _scope
    -0.14
    uluk
    -0.14
    itting
    -0.14
    uyu
    -0.14
    POSITIVE LOGITS
    aby
    0.16
    arb
    0.16
    aru
    0.16
    stad
    0.15
     ontvangst
    0.15
    à¥įध
    0.15
    isle
    0.15
    apult
    0.15
    ombat
    0.14
    arin
    0.14
    Act Density 0.004%

    No Known Activations