INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    %i
    -0.07
     comparative
    -0.07
    zsche
    -0.07
     Deutsche
    -0.07
     additive
    -0.06
    Percent
    -0.06
     rte
    -0.06
    -0.06
     Narc
    -0.06
     Burke
    -0.06
    POSITIVE LOGITS
     window
    0.11
     Window
    0.11
    Window
    0.10
     окон
    0.08
    .window
    0.08
     WINDOW
    0.08
     windows
    0.07
    ON
    0.07
    window
    0.07
    WINDOWS
    0.07
    Act Density 0.027%

    No Known Activations