INDEX
    Explanations

    names and references related to characters and elements in comic books or superhero stories

    New Auto-Interp
    Negative Logits
    iat
    -0.15
    ersion
    -0.15
     PJ
    -0.14
    eil
    -0.14
    canf
    -0.14
     Gast
    -0.14
    ầm
    -0.14
    ee
    -0.14
     umb
    -0.13
    emente
    -0.13
    POSITIVE LOGITS
    ninger
    0.16
     treff
    0.16
    izons
    0.15
     Dias
    0.15
     allergic
    0.14
    vault
    0.14
     addCriterion
    0.14
    868
    0.14
    693
    0.14
    hora
    0.14
    Act Density 0.008%

    No Known Activations