INDEX
    Explanations

    mentions of Turkey and its geopolitical relationships

    New Auto-Interp
    Negative Logits
    utow
    -0.15
    ÏĦÏħ
    -0.15
    apro
    -0.14
     Å
    -0.14
     Sheldon
    -0.14
    çº
    -0.14
    ucky
    -0.14
     Chic
    -0.14
    uben
    -0.14
    _MA
    -0.13
    POSITIVE LOGITS
    adem
    0.15
    oy
    0.15
    unma
    0.14
    ATES
    0.14
    yar
    0.14
    æ§ĺ
    0.14
    .ylim
    0.14
    æ³³
    0.14
    деÑĢ
    0.13
     Yar
    0.13
    Act Density 0.078%

    No Known Activations