INDEX
    Explanations

    phrases related to comic books

    references to comic books

    New Auto-Interp
    Negative Logits
    igated
    -0.76
     Blooming
    -0.67
    edIn
    -0.67
    holm
    -0.66
    ldon
    -0.65
    ntil
    -0.64
    doors
    -0.64
    ª
    -0.63
    gren
    -0.63
    come
    -0.63
    POSITIVE LOGITS
     book
    1.14
     strip
    1.06
    strip
    1.04
     books
    1.03
     strips
    1.02
    book
    0.98
     Comics
    0.96
    ograp
    0.95
     relief
    0.95
     comics
    0.87
    Act Density 0.046%

    No Known Activations