INDEX
    Explanations

    specific names and references related to art and culture

    New Auto-Interp
    Negative Logits
    iÄħ
    -0.14
    cline
    -0.14
     leaking
    -0.14
    izzer
    -0.13
    ška
    -0.13
    onal
    -0.13
    anax
    -0.13
    æ§
    -0.13
    pline
    -0.13
    .pad
    -0.13
    POSITIVE LOGITS
    ov
    0.43
    ova
    0.40
    ev
    0.30
    eva
    0.29
    OV
    0.29
    enko
    0.29
    ова
    0.28
    off
    0.28
    enco
    0.27
    ovich
    0.27
    Act Density 0.071%

    No Known Activations