INDEX
    Explanations

    mentions of governors and their actions relating to state policies

    New Auto-Interp
    Negative Logits
    orer
    -0.17
    oog
    -0.15
    edi
    -0.15
    enko
    -0.14
    ull
    -0.14
     Gins
    -0.14
    umin
    -0.14
    ucene
    -0.14
    yb
    -0.14
    elem
    -0.13
    POSITIVE LOGITS
    ships
    0.17
    licht
    0.16
    abcdefghijkl
    0.16
    онÑĮ
    0.16
    onna
    0.16
    lush
    0.15
    ship
    0.15
    readcr
    0.14
     yyn
    0.14
    tridges
    0.14
    Act Density 0.021%

    No Known Activations