INDEX
    Explanations

    words related to national identity and governance

    New Auto-Interp
    Negative Logits
    /he
    -0.18
    :UITableView
    -0.15
    ÑģÑı
    -0.15
    337
    -0.15
    anuts
    -0.15
    preci
    -0.15
    itage
    -0.14
    angel
    -0.14
    thing
    -0.14
    گاÙĩ
    -0.14
    POSITIVE LOGITS
    /global
    0.21
    wide
    0.21
    /local
    0.20
    /world
    0.18
    /reg
    0.18
    -wide
    0.18
    ization
    0.18
    ized
    0.17
    izing
    0.17
    izers
    0.17
    Act Density 0.045%

    No Known Activations