INDEX
    Explanations

    names of people and characters

    New Auto-Interp
    Negative Logits
    https
    0.47
     spp
    0.44
    www
    0.42
    noun
    0.41
    feat
    0.41
    cia
    0.39
    ·
    0.39
     FormsModule
    0.39
    場合がございます
    0.38
    0.38
    POSITIVE LOGITS
     Lady
    0.82
     Alfred
    0.80
     Charles
    0.77
     Sir
    0.76
     Teddy
    0.76
     Emperor
    0.76
     George
    0.76
     Monsieur
    0.74
     Dante
    0.74
     Hitler
    0.74
    Act Density 0.316%

    No Known Activations