INDEX
    Explanations

    phrases related to societal issues, particularly those involving governance and rights

    New Auto-Interp
    Negative Logits
     ones
    -0.20
     Ones
    -0.17
    rippling
    -0.17
    ones
    -0.15
    ENSOR
    -0.14
    εÏĦ
    -0.14
    loat
    -0.14
    ำ
    -0.14
    rier
    -0.14
    onto
    -0.14
    POSITIVE LOGITS
     everywhere
    0.17
    ä½ľä¸º
    0.15
     itself
    0.15
    .topic
    0.14
     Topic
    0.13
    одÑĥ
    0.13
    ustin
    0.13
    yles
    0.13
    estre
    0.13
    topic
    0.13
    Act Density 0.493%

    No Known Activations