INDEX
    Explanations

    themes related to racial justice and community engagement

    New Auto-Interp
    Negative Logits
    epend
    -0.16
    μί
    -0.15
    رÙĪØ²
    -0.15
    ayah
    -0.15
    à¹Ģà¸ŀล
    -0.14
    greso
    -0.14
    pps
    -0.14
    dik
    -0.13
    eba
    -0.13
    adero
    -0.13
    POSITIVE LOGITS
     problem
    0.28
     interrog
    0.27
     gr
    0.27
     decent
    0.27
     question
    0.25
     foreground
    0.24
     trouble
    0.24
     privilege
    0.23
     challenge
    0.23
     privileges
    0.22
    Act Density 0.161%

    No Known Activations