INDEX
    Explanations

    references to individuals and their roles in societal or systemic contexts

    New Auto-Interp
    Negative Logits
     ÑĦон
    -0.14
    âĪı
    -0.14
    orex
    -0.14
    utz
    -0.14
    üme
    -0.14
    atz
    -0.14
    Rib
    -0.13
     Fon
    -0.13
    dorf
    -0.13
    /REC
    -0.13
    POSITIVE LOGITS
     being
    0.24
    being
    0.19
     Being
    0.17
    à¸į
    0.15
    CellValue
    0.15
    Being
    0.15
    ãĥĹãĥ¬
    0.14
    ooke
    0.14
     having
    0.14
     Spl
    0.14
    Act Density 0.353%

    No Known Activations