INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    in
    1.78
    and
    1.58
     for
    1.53
    it
    1.49
    ac
    1.45
     can
    1.34
     and
    1.30
    can
    1.28
    та
    1.27
    ie
    1.25
    POSITIVE LOGITS
     
    1.02
     is
    0.87
     **
    0.81
     находя
    0.81
    𝐤
    0.81
    0.80
    𝐳
    0.79
     Mourinho
    0.76
    isinde
    0.75
    ”,“
    0.73
    Act Density 2.495%

    No Known Activations