INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ви
    1.30
    ва
    1.27
    ни
    1.23
    ну
    1.20
    <0x80>
    1.13
    ці
    1.07
    ції
    1.04
    ד
    0.98
    0.98
    ій
    0.96
    POSITIVE LOGITS
    -
    1.16
    u
    1.08
    ك
    1.08
    R
    1.04
    N
    0.94
    ies
    0.92
    k
    0.92
    bies
    0.91
    c
    0.89
    L
    0.89
    Act Density 0.019%

    No Known Activations