INDEX
    Explanations

    expressions of magical realism and fantastical elements

    New Auto-Interp
    Negative Logits
    _ARGS
    -0.15
     OMG
    -0.15
    ewise
    -0.14
     Libre
    -0.14
     loads
    -0.14
     Darling
    -0.14
    opi
    -0.13
    rame
    -0.13
     tons
    -0.13
    ama
    -0.13
    POSITIVE LOGITS
    unar
    0.21
    羣æĺ¯
    0.19
    uze
    0.17
     sometimes
    0.17
    isz
    0.16
     huh
    0.16
    ccb
    0.15
    ìĹŃìĭľ
    0.15
     Cf
    0.15
     apparently
    0.15
    Act Density 0.362%

    No Known Activations