INDEX
    Explanations

    references to anime and related terms

    mentions of anime and related content

    New Auto-Interp
    Negative Logits
    bledon
    -0.88
    lain
    -0.86
    asser
    -0.82
    riers
    -0.81
    20439
    -0.77
    ntil
    -0.76
    cair
    -0.76
    pes
    -0.76
    urion
    -0.72
    pse
    -0.71
    POSITIVE LOGITS
     adaptation
    0.92
     fandom
    0.92
     manga
    0.91
     anime
    0.89
    acters
    0.87
    Japan
    0.84
     studios
    0.82
     studio
    0.79
     Anime
    0.78
     series
    0.78
    Act Density 0.065%

    No Known Activations