INDEX
    Explanations

    eager agreement to start

    New Auto-Interp
    Negative Logits
    Interesting
    0.48
     Interesting
    0.47
     interesting
    0.46
     интересный
    0.46
     interesante
    0.44
     respected
    0.43
     respectful
    0.42
    尊重
    0.41
     interessante
    0.41
     intéressante
    0.41
    POSITIVE LOGITS
    Yay
    1.72
     Yay
    1.63
     yay
    1.51
    yay
    1.46
     Woo
    1.34
    Woo
    1.23
    woo
    1.15
     woo
    1.13
    🎉
    1.09
     🎉
    1.07
    Act Density 0.086%

    No Known Activations