INDEX
    Explanations

    mentions of the city Tokyo

    New Auto-Interp
    Negative Logits
    hemy
    -0.84
    edly
    -0.82
    inelli
    -0.81
    vantage
    -0.79
    rals
    -0.75
    estern
    -0.73
    ibilities
    -0.72
    mble
    -0.71
    ebook
    -0.71
    Ö¼
    -0.70
    POSITIVE LOGITS
     Dome
    0.91
     Disneyland
    0.83
     Babel
    0.83
     Bay
    0.77
    Tok
    0.77
     Harbour
    0.76
     Metropolitan
    0.75
    ichi
    0.74
     Lumpur
    0.74
     Mirage
    0.74
    Act Density 0.004%

    No Known Activations