INDEX
    Explanations

    Chinese poets Li Bai, Du Fu

    New Auto-Interp
    Negative Logits
    ----------------------------------------------------------------
    -0.08
     hide
    -0.08
    mik
    -0.07
     sleeve
    -0.07
     nha
    -0.07
    usions
    -0.07
    aces
    -0.07
    伦理
    -0.07
     hql
    -0.07
     bande
    -0.07
    POSITIVE LOGITS
    dığı
    0.08
    Great
    0.08
     Great
    0.07
    gets
    0.07
    jin
    0.07
    .(*
    0.07
    slow
    0.07
     Tack
    0.07
    .mapper
    0.07
    Absolutely
    0.07
    Act Density 0.002%

    No Known Activations