INDEX
    Explanations

    references to superhero characters and their associated films

    New Auto-Interp
    Negative Logits
     للاسماء
    -0.45
     StringTokenizer
    -0.44
    cipar
    -0.42
     OkHttpClient
    -0.41
    ukone
    -0.40
    tangentMode
    -0.39
    -0.39
    rsiniz
    -0.38
    hoeddwyd
    -0.37
    `}`,
    -0.37
    POSITIVE LOGITS
     Batman
    0.56
    Batman
    0.54
     superhero
    0.53
     batman
    0.52
     InputDecoration
    0.48
     superheroes
    0.47
    batman
    0.44
     leſs
    0.44
     vigilante
    0.42
     myſelf
    0.41
    Act Density 0.594%

    No Known Activations