INDEX
    Explanations

    phrases related to social identity and marginalized communities

    New Auto-Interp
    Negative Logits
    ioni
    -0.17
    zim
    -0.16
    ghan
    -0.16
    .typ
    -0.15
     thức
    -0.14
     नव
    -0.14
    ifo
    -0.14
     Leben
    -0.13
    iton
    -0.13
    .EventQueue
    -0.13
    POSITIVE LOGITS
     whom
    0.25
     ages
    0.18
    etta
    0.17
     stature
    0.17
    /vendors
    0.16
     Ages
    0.16
     who
    0.16
    607
    0.15
     integrity
    0.14
     Cro
    0.14
    Act Density 0.050%

    No Known Activations