INDEX
    Explanations

    references to specific characters and events within the "My Hero Academia" series

    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -1.02
    ReusableCell
    -1.00
    ]")]
    -0.79
    Personensuche
    -0.78
    دانشنامهٔ
    -0.77
     &___
    -0.77
    NameInMap
    -0.70
     ModelExpression
    -0.68
     PhpStorm
    -0.68
     Lightboxes
    -0.68
    POSITIVE LOGITS
     manga
    0.63
     anime
    0.59
    ősz
    0.54
     Manga
    0.49
     mangá
    0.47
    anime
    0.47
     sanitaires
    0.45
     аниме
    0.45
    utri
    0.45
     Fiore
    0.44
    Act Density 0.436%

    No Known Activations