INDEX
    Explanations

    references to historical events and their consequences, particularly related to the Jewish community during World War II

    New Auto-Interp
    Negative Logits
    egie
    -0.21
    nts
    -0.16
    ahoma
    -0.16
    rell
    -0.16
    illes
    -0.15
    ảnh
    -0.15
    iges
    -0.14
    prise
    -0.14
     voiture
    -0.14
     experi
    -0.14
    POSITIVE LOGITS
    quel
    0.24
     premier
    0.19
     même
    0.18
     tiers
    0.17
     Kremlin
    0.17
     temps
    0.17
     fame
    0.17
     genre
    0.17
     sein
    0.16
    isure
    0.16
    Act Density 0.024%

    No Known Activations