INDEX
    Explanations

    references to ancient civilizations or historical contexts

    New Auto-Interp
    Negative Logits
    ution
    -0.15
    ì¦Į
    -0.15
    uche
    -0.15
    çİĩ
    -0.14
    аÑĤов
    -0.14
    mers
    -0.14
    taÅŁ
    -0.14
    tabpanel
    -0.14
    ubre
    -0.14
    ücken
    -0.14
    POSITIVE LOGITS
    illary
    0.42
    ient
    0.35
    ients
    0.32
    IENT
    0.31
    ien
    0.28
    ienne
    0.23
    illi
    0.23
    ill
    0.22
    stral
    0.21
    iento
    0.20
    Act Density 0.008%

    No Known Activations