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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    뷁
    -0.08
    sigma
    -0.08
     kişinin
    -0.08
    俾
    -0.07
    Mos
    -0.07
    ifferences
    -0.07
     baru
    -0.07
    ńsk
    -0.07
     ale
    -0.07
     ngươi
    -0.07
    POSITIVE LOGITS
    后面的
    0.09
     Чи
    0.07
    齐鲁
    0.07
     Fl
    0.07
    흗
    0.07
     tid
    0.07
    잴
    0.07
    很好
    0.07
     strawberries
    0.07
    底
    0.07
    Act Density 0.029%

    No Known Activations