INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    hello
    1.14
     hello
    1.02
    Hello
    1.00
    Hi
    0.93
    안녕하세요
    0.91
     Hello
    0.90
     merhaba
    0.90
    Hallo
    0.89
     hi
    0.88
    你好
    0.86
    POSITIVE LOGITS
     Hearings
    0.85
     economists
    0.82
     hearings
    0.82
     symposium
    0.81
     Mormon
    0.79
     CFP
    0.78
     Litigation
    0.76
     appropriations
    0.76
     Jefferson
    0.75
     satire
    0.74
    Act Density 0.002%

    No Known Activations