INDEX
    Explanations

    questions, thanks, and informal remarks

    New Auto-Interp
    Negative Logits
    💀
    1.18
     :/
    1.13
     xD
    1.08
     fucking
    1.02
    1.01
     fucked
    1.00
     idk
    0.99
     fuck
    0.96
    👾
    0.95
    ⚠️
    0.93
    POSITIVE LOGITS
     Incidentally
    1.21
    Incidentally
    1.16
     Guess
    1.08
    Wouldn
    1.04
     incidentally
    0.97
     guess
    0.96
    Gee
    0.96
     Believe
    0.95
    Guess
    0.94
     terrific
    0.93
    Act Density 0.027%

    No Known Activations