INDEX
    Explanations

    references to humor and comedic elements in discussions about film and characters

    New Auto-Interp
    Negative Logits
    pector
    -0.15
    оÑģÑĮ
    -0.15
    á»ijng
    -0.15
     spraying
    -0.14
    ãĥ³ãĤ°ãĥ«
    -0.14
    atatype
    -0.14
     dispers
    -0.14
    ocator
    -0.14
    elson
    -0.14
    lsen
    -0.13
    POSITIVE LOGITS
     Ser
    0.29
     Fire
    0.29
     Shepherd
    0.28
    Fire
    0.22
     Jay
    0.21
     River
    0.21
     Shepard
    0.20
     Alliance
    0.20
     Wash
    0.20
     Mal
    0.20
    Act Density 0.009%

    No Known Activations