INDEX
    Explanations

    specific comic book titles and references

    New Auto-Interp
    Negative Logits
    itag
    -0.15
    ahlen
    -0.15
    κι
    -0.15
    iyas
    -0.15
    zimmer
    -0.15
    ġ
    -0.14
    erti
    -0.14
     spoken
    -0.14
    kits
    -0.14
    etur
    -0.13
    POSITIVE LOGITS
     Comics
    0.18
    LEMENT
    0.17
     comics
    0.16
     Syntax
    0.15
     comic
    0.15
     Manning
    0.14
    oves
    0.14
    важа
    0.14
    emek
    0.13
    388
    0.13
    Act Density 0.063%

    No Known Activations