INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.94
     всё
    0.82
     где
    0.79
     rife
    0.79
     largely
    0.79
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.78
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.77
     paramount
    0.77
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.75
     enthr
    0.75
    POSITIVE LOGITS
     Typical
    1.18
    正确的
    1.17
     typical
    1.15
     standard
    1.15
     correct
    1.15
     стандарт
    1.13
     usual
    1.12
    典型
    1.11
    標準
    1.09
    标准的
    1.07
    Act Density 0.604%

    No Known Activations