INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.07
     plutôt
    -0.07
     Gly
    -0.07
    let
    -0.06
    entrada
    -0.06
    -0.06
    bec
    -0.06
     ̄ ̄ ̄
    -0.06
     wlan
    -0.06
    ;"↵
    -0.06
    POSITIVE LOGITS
     Bush
    0.12
    Bush
    0.12
     bush
    0.09
    425
    0.08
     bushes
    0.07
    [sub
    0.07
     Republican
    0.06
     BrowserRouter
    0.06
     Buck
    0.06
     Bu
    0.06
    Act Density 0.003%

    No Known Activations