INDEX
    Explanations

    words related to storytelling and narrative elements in texts

    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.68
    CopyWith
    -0.65
    ParallelGroup
    -0.61
    oa̍t
    -0.56
    NameInMap
    -0.54
    WireFormatLite
    -0.52
    ########.
    -0.48
    hollywood
    -0.48
    ConverterFactory
    -0.47
    enumii
    -0.47
    POSITIVE LOGITS
     book
    0.82
     film
    0.73
     game
    0.73
     title
    0.69
     album
    0.69
     poem
    0.66
     película
    0.64
     juego
    0.63
     song
    0.61
     filmen
    0.61
    Act Density 0.522%

    No Known Activations