INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     THANK
    0.77
     thank
    0.73
     Thank
    0.72
    THANK
    0.66
    Thank
    0.64
    thank
    0.56
     Здравствуйте
    0.50
     hello
    0.49
     Congratulations
    0.49
     congratulations
    0.49
    POSITIVE LOGITS
    Cheers
    1.04
     cheers
    0.95
     Cheers
    0.93
     reckons
    0.64
     reckon
    0.60
    Hey
    0.58
    Yep
    0.58
    Yeah
    0.57
    che
    0.57
    Ta
    0.57
    Act Density 0.032%

    No Known Activations