INDEX
    Explanations

    titles of films and their sequels

    New Auto-Interp
    Negative Logits
     Bros
    -0.15
    _intr
    -0.15
     Beit
    -0.14
    chwitz
    -0.14
     eg
    -0.14
     Becker
    -0.13
    usercontent
    -0.13
     Chan
    -0.13
    aris
    -0.13
    _member
    -0.13
    POSITIVE LOGITS
    ä½ľèĢħ
    0.19
    -themed
    0.17
    anness
    0.16
     movie
    0.15
    omik
    0.15
    -inspired
    0.15
    /copyleft
    0.15
    ittings
    0.14
    .chapter
    0.14
    -era
    0.14
    Act Density 0.158%

    No Known Activations