INDEX
    Explanations

    phrases related to educational institutions and student demographics

    New Auto-Interp
    Negative Logits
     synd
    -0.16
     Synd
    -0.15
    uluk
    -0.15
    kova
    -0.14
    nex
    -0.14
    untas
    -0.13
    .wallet
    -0.13
     Fra
    -0.13
    ç´¯
    -0.13
     squ
    -0.13
    POSITIVE LOGITS
    ourke
    0.15
    dio
    0.14
     Toro
    0.14
    ystack
    0.14
    lify
    0.14
    ana
    0.14
    Disp
    0.14
    lene
    0.14
    icter
    0.13
    enko
    0.13
    Act Density 0.005%

    No Known Activations