INDEX
    Explanations

    attends to the tokens representing HTML or button elements from other unnamed tokens adjacent to them

    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.11
    2:0.10
    3:0.07
    4:0.09
    5:0.26
    6:0.11
    7:0.12
    Negative Logits
    ViewImports
    -0.28
     normais
    -0.27
    améli
    -0.27
    zość
    -0.26
     Савезне
    -0.26
     positivas
    -0.25
    ัติ
    -0.25
     vermelhas
    -0.25
     vermelha
    -0.24
     negativas
    -0.24
    POSITIVE LOGITS
    fromCharCode
    0.27
     للمعارف
    0.26
    Населення
    0.26
    kháu
    0.26
    aarrggbb
    0.25
    0.25
     FormControl
    0.24
     bean
    0.24
    Twig
    0.24
    gatsby
    0.24
    Act Density 0.019%

    No Known Activations