INDEX
    Explanations

    terms related to socio-economic and political issues

    New Auto-Interp
    Negative Logits
    erson
    -0.14
    aret
    -0.14
    .dot
    -0.14
    äre
    -0.14
    ÑĢаÑħов
    -0.14
    anja
    -0.13
    743
    -0.13
    -dot
    -0.13
    ër
    -0.13
    icult
    -0.13
    POSITIVE LOGITS
    ackbar
    0.18
    æº
    0.17
    aat
    0.16
    inds
    0.15
    OTA
    0.15
    otas
    0.15
    emens
    0.14
    обов
    0.14
    esters
    0.14
    IGNED
    0.14
    Act Density 0.011%

    No Known Activations