INDEX
    Explanations

    mathematical notation

    New Auto-Interp
    Negative Logits
    (dat
    -0.08
    (car
    -0.08
     Cara
    -0.07
    -0.07
    .car
    -0.07
     Ops
    -0.07
     carrying
    -0.07
    (Car
    -0.07
    FUNC
    -0.07
     causing
    -0.07
    POSITIVE LOGITS
     губ
    0.09
     negate
    0.08
    0.08
     primary
    0.08
     novamente
    0.08
     participant
    0.08
     Newcastle
    0.08
    主体
    0.08
     participante
    0.08
    0.08
    Act Density 0.047%

    No Known Activations