INDEX
    Explanations

    expressions of absurdity and frustration regarding societal issues

    New Auto-Interp
    Negative Logits
    IU
    -0.16
    ¼åIJĪ
    -0.15
    ylan
    -0.14
    esin
    -0.14
    specifier
    -0.14
    .pb
    -0.14
    ereco
    -0.14
    apiro
    -0.14
    @author
    -0.14
    loom
    -0.13
    POSITIVE LOGITS
     worse
    0.17
    lag
    0.15
    oki
    0.15
     Inf
    0.14
    uppe
    0.14
     Worse
    0.14
    Inf
    0.13
     thread
    0.13
    ocr
    0.13
    kip
    0.13
    Act Density 0.387%

    No Known Activations