INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     пови
    0.40
    stationary
    0.35
    0.34
    Pretty
    0.34
     tasmim
    0.33
    🙁
    0.32
    дії
    0.32
    mensaje
    0.32
     выс
    0.32
    ЛЯ
    0.31
    POSITIVE LOGITS
     importantly
    1.72
     Importantly
    1.26
     crucially
    1.09
     interestingly
    0.91
    重要的是
    0.90
     notably
    0.78
     impressively
    0.78
     critically
    0.68
     significantly
    0.67
    cially
    0.66
    Act Density 0.020%

    No Known Activations