INDEX
    Explanations

    mentions of military actions and tensions involving the US and Iran

    New Auto-Interp
    Negative Logits
    upe
    -0.18
    anye
    -0.15
    $MESS
    -0.15
    ollo
    -0.14
    ermint
    -0.14
    duino
    -0.14
    .timeScale
    -0.14
    nyder
    -0.14
    ~-~-~-~-
    -0.13
    oyo
    -0.13
    POSITIVE LOGITS
     silent
    0.15
    šak
    0.14
    lope
    0.14
     Liver
    0.14
    ute
    0.14
    -static
    0.14
     Perez
    0.13
    SSI
    0.13
    DL
    0.13
    aly
    0.13
    Act Density 0.113%

    No Known Activations