INDEX
    Explanations

    Carl and Karl followed by names

    New Auto-Interp
    Negative Logits
    大众
    0.42
     Underlying
    0.42
    লার
    0.41
    Expecting
    0.38
    Extraction
    0.38
    Titanic
    0.38
    期待
    0.37
     کوردستان
    0.37
    czaj
    0.37
    Voids
    0.36
    POSITIVE LOGITS
     Marx
    0.55
    isle
    0.52
     Friedrich
    0.51
    ifornia
    0.50
     Karl
    0.50
    otta
    0.50
    sruhe
    0.49
     Carl
    0.47
    ito
    0.45
    itos
    0.45
    Act Density 0.001%

    No Known Activations