INDEX
    Explanations

    themes related to social justice and activism

    New Auto-Interp
    Negative Logits
    aris
    -0.21
    cow
    -0.17
    fila
    -0.15
     taraf
    -0.15
    šov
    -0.15
    enden
    -0.14
    ori
    -0.14
    upply
    -0.14
    æĿ¿
    -0.14
    orne
    -0.14
    POSITIVE LOGITS
    ledon
    0.15
    kiem
    0.15
    clc
    0.15
    ocale
    0.14
    PropTypes
    0.14
     Kı
    0.14
     OPC
    0.14
     Gilles
    0.13
    ,void
    0.13
    essim
    0.13
    Act Density 0.189%

    No Known Activations