INDEX
    Explanations

    UI containers and elements

    New Auto-Interp
    Negative Logits
     artyku
    0.48
     produkty
    0.45
    iniai
    0.43
     источ
    0.43
    চলে
    0.42
     статью
    0.42
     articoli
    0.41
     prodotto
    0.41
     источников
    0.41
     produtos
    0.40
    POSITIVE LOGITS
     wrapper
    0.56
     inner
    0.55
    inner
    0.55
    outer
    0.54
    wrapper
    0.48
     outer
    0.47
    Inner
    0.47
    infix
    0.46
    mask
    0.45
     mask
    0.44
    Act Density 0.014%

    No Known Activations