INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    eru
    -0.08
     Leo
    -0.07
     tří
    -0.07
     broccoli
    -0.07
     Seymour
    -0.07
     jejím
    -0.07
     prov
    -0.07
    -0.06
    advert
    -0.06
     kriz
    -0.06
    POSITIVE LOGITS
     hand
    0.14
     Hand
    0.13
     hands
    0.13
    Hand
    0.11
     Hands
    0.11
    hands
    0.11
     handed
    0.11
    hand
    0.10
     HAND
    0.10
    Hands
    0.10
    Act Density 0.032%

    No Known Activations