INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     egregious
    0.45
     billionaire
    0.43
     freshman
    0.43
     marquee
    0.41
     apiece
    0.41
     athletic
    0.40
     interracial
    0.40
    ayscale
    0.40
     resumes
    0.39
    0.38
    POSITIVE LOGITS
     Swedish
    1.38
    Swedish
    1.38
     Gothenburg
    1.32
     Göteborg
    1.21
     Sweden
    1.15
     সুইড
    1.13
     Uppsala
    1.11
     Å
    1.10
     Sverige
    1.10
    swedish
    1.08
    Act Density 0.018%

    No Known Activations