INDEX
    Explanations

    political figures and names

    New Auto-Interp
    Negative Logits
    如果我们
    0.73
     ако
    0.67
     якщо
    0.64
    我们会
    0.63
    если
    0.63
     мы
    0.62
     ANYTHING
    0.62
     ถ้า
    0.62
     если
    0.61
     nếu
    0.60
    POSITIVE LOGITS
     According
    0.75
    Due
    0.71
     Interestingly
    0.71
     Currently
    0.70
     according
    0.69
     notable
    0.68
    Interestingly
    0.68
     Notable
    0.67
     Notably
    0.66
     due
    0.66
    Act Density 0.036%

    No Known Activations