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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     বেশী
    0.87
     incluyendo
    0.87
     чтоб
    0.85
     diatas
    0.83
     kì
    0.82
     अक्सर
    0.81
     icin
    0.80
     &/
    0.78
     щоб
    0.76
     yg
    0.75
    POSITIVE LOGITS
     آقای
    0.77
     그다음에
    0.75
     парламента
    0.73
    That
    0.71
     memorandum
    0.69
    Parliament
    0.68
    我认为
    0.68
    ということ
    0.68
    すごく
    0.65
    forward
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.