INDEX
    Explanations

    references to geopolitical events and relations, particularly involving Iran

    New Auto-Interp
    Negative Logits
    -insert
    -0.16
     ÙħذÙĩ
    -0.15
    ucz
    -0.15
    urum
    -0.15
    ctal
    -0.15
    ÙĪØº
    -0.15
    826
    -0.15
    ashi
    -0.15
    -worker
    -0.14
    shal
    -0.14
    POSITIVE LOGITS
     Horm
    0.21
     Mehr
    0.18
     Fate
    0.17
     Rae
    0.17
     Tas
    0.17
     Wendy
    0.17
     Tehran
    0.17
     Resistance
    0.17
     Leader
    0.16
     intl
    0.16
    Act Density 0.031%

    No Known Activations