INDEX
    Explanations

    the name "Putin" in various contexts

    mentions of Vladimir Putin

    New Auto-Interp
    Negative Logits
    Thom
    -0.80
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.77
    ibles
    -0.75
    ITNESS
    -0.75
    IENT
    -0.74
    ANE
    -0.73
    ppelin
    -0.70
    IRD
    -0.69
     Honolulu
    -0.69
     Kear
    -0.67
    POSITIVE LOGITS
     Jinping
    1.14
    cius
    0.95
     annexed
    0.94
     Putin
    0.91
    otti
    0.84
    iets
    0.81
     rall
    0.80
     dictator
    0.77
     dictatorship
    0.76
    sky
    0.76
    Act Density 0.020%

    No Known Activations