INDEX
    Explanations

    references to fraternities and sororities within college organizations

    New Auto-Interp
    Negative Logits
    fur
    -0.16
    chter
    -0.16
    apan
    -0.15
    lis
    -0.14
    anchor
    -0.14
     Uhr
    -0.14
    iaz
    -0.14
    eric
    -0.14
    peq
    -0.14
     пеÑĢен
    -0.14
    POSITIVE LOGITS
     organisation
    0.15
    ruc
    0.14
     antis
    0.14
     Barg
    0.14
    parer
    0.14
    ĭ
    0.14
     spl
    0.14
     memberships
    0.14
     Rox
    0.14
     Scal
    0.14
    Act Density 0.197%

    No Known Activations