INDEX
    Explanations

    words related to Polish culture and heritage

    New Auto-Interp
    Negative Logits
    chio
    -0.17
    ussen
    -0.17
    ainen
    -0.17
    ãĥ³
    -0.16
    mans
    -0.15
    ëŀ¨
    -0.14
     circles
    -0.14
    astes
    -0.14
    ãĥ¼ãĥģ
    -0.13
    raq
    -0.13
    POSITIVE LOGITS
    ÄĻki
    0.15
    رÙĪØ²
    0.15
    à¤¾à¤ł
    0.14
    uck
    0.14
    borg
    0.14
    glich
    0.14
    uce
    0.14
    oucÃŃ
    0.13
     Bien
    0.13
    bel
    0.13
    Act Density 0.044%

    No Known Activations