INDEX
    Explanations

    instances of systemic criticism and accountability issues related to social justice and institutional practices

    New Auto-Interp
    Negative Logits
    تÙĬÙĨ
    -0.16
     Binder
    -0.14
     Mö
    -0.14
    uyên
    -0.14
     Shepherd
    -0.14
    _spectrum
    -0.14
    /***/
    -0.14
     eskort
    -0.13
    lia
    -0.13
    noDB
    -0.13
    POSITIVE LOGITS
     too
    0.20
     TOO
    0.19
    too
    0.18
     zbyt
    0.17
    -too
    0.17
    uset
    0.17
    cth
    0.17
     Too
    0.16
    ifest
    0.16
    太
    0.16
    Act Density 0.140%

    No Known Activations