INDEX
    Explanations

    phrases related to activism and social justice issues

    New Auto-Interp
    Negative Logits
     Gall
    -0.15
    inas
    -0.14
    itzer
    -0.14
    ãĥ¼ãĥī
    -0.14
    aris
    -0.13
    ë¹ĦìķĦ
    -0.13
    878
    -0.13
    ena
    -0.13
    robe
    -0.13
    omo
    -0.13
    POSITIVE LOGITS
    οι
    0.18
    aign
    0.14
    .mixin
    0.14
    .names
    0.13
     Queen
    0.13
     pull
    0.13
    ÐĴС
    0.13
     ëĮĢìĥģ
    0.13
    oje
    0.13
     Prefer
    0.13
    Act Density 0.266%

    No Known Activations