INDEX
    Explanations

    themes related to anti-authoritarianism and social justice

    New Auto-Interp
    Negative Logits
     tilt
    -0.15
    itag
    -0.14
     replay
    -0.14
    ìĮ
    -0.14
    .kr
    -0.14
     spyOn
    -0.13
    _ENGINE
    -0.13
    umin
    -0.13
    enting
    -0.13
    urb
    -0.13
    POSITIVE LOGITS
     canon
    0.17
     writers
    0.16
     canonical
    0.15
    (writer
    0.15
    eyer
    0.15
     writer
    0.15
    ovky
    0.14
     ori
    0.14
    ÑĤÑĢон
    0.14
     appearances
    0.14
    Act Density 0.068%

    No Known Activations