INDEX
    Explanations

    references to gender and inclusivity in relation to social issues or conditions

    New Auto-Interp
    Negative Logits
    ivid
    -0.15
    ichen
    -0.15
     dia
    -0.14
    ihar
    -0.14
    åij½
    -0.14
    istinguished
    -0.14
    tridge
    -0.14
    inder
    -0.14
    obao
    -0.14
    ano
    -0.14
    POSITIVE LOGITS
    AYS
    0.15
    ancel
    0.14
     alike
    0.14
     aalborg
    0.14
    olatile
    0.14
    úb
    0.14
     Skip
    0.14
    bek
    0.13
     Anthem
    0.13
    odes
    0.13
    Act Density 0.244%

    No Known Activations