INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Bowling
    0.61
    ,<
    0.60
    Helm
    0.59
     lumineux
    0.59
     belladone
    0.58
    Bowling
    0.58
    ègre
    0.57
     Helmet
    0.57
     sillonné
    0.55
     réseau
    0.54
    POSITIVE LOGITS
    Pairs
    0.61
    pair
    0.61
     pairs
    0.61
    对其
    0.60
     pair
    0.60
     Pair
    0.58
    pairs
    0.58
    PAIR
    0.58
     zoveel
    0.57
    Pair
    0.55
    Act Density 0.002%

    No Known Activations