Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    。
    0.63
     geeignet
    0.59
    Using
    0.57
     。
    0.57
    ።
    0.57
    Телефон
    0.56
    EG
    0.55
    %。
    0.55
    ちなみに
    0.55
    ۔
    0.54
    POSITIVE LOGITS
     demeanor
    0.69
     deviations
    0.68
     announcing
    0.68
     announcements
    0.68
    щать
    0.68
     strokes
    0.66
     tattoos
    0.66
     attribution
    0.65
     overload
    0.65
     malfunctions
    0.65
    Act Density 0.001%

    No Known Activations