INDEX
    Explanations

    words related to societal issues and challenges

    New Auto-Interp
    Negative Logits
    uby
    -0.15
    rees
    -0.15
    contres
    -0.15
    iap
    -0.14
    iversite
    -0.14
    ORITY
    -0.13
    iÄħ
    -0.13
    gia
    -0.13
     Lookup
    -0.13
    /display
    -0.13
    POSITIVE LOGITS
    incinn
    0.17
    aver
    0.16
    ghan
    0.15
    боÑĤ
    0.15
    esar
    0.14
    brit
    0.14
    ahan
    0.14
    iver
    0.14
    kbd
    0.14
    agos
    0.14
    Act Density 0.026%

    No Known Activations