INDEX
    Explanations

    mentions of "Russian" in various contexts

    New Auto-Interp
    Negative Logits
    Score
    -0.80
    erer
    -0.80
    enance
    -0.73
    odder
    -0.72
     Starr
    -0.71
    ridges
    -0.70
    ttes
    -0.70
     Blazers
    -0.68
    ording
    -0.68
    ecause
    -0.67
    POSITIVE LOGITS
     Federation
    1.16
     Orthodox
    0.93
     olig
    0.88
     nationals
    0.86
     rou
    0.82
     separatists
    0.82
     annexed
    0.80
     Rou
    0.79
     Embassy
    0.78
     nesting
    0.78
    Act Density 0.017%

    No Known Activations