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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     stress
    -0.07
     עושים
    -0.07
    功率
    -0.06
     nu
    -0.06
    自然灾害
    -0.06
    暴
    -0.06
    Mutable
    -0.06
     Potential
    -0.06
    *(
    -0.06
    pane
    -0.06
    POSITIVE LOGITS
     програм
    0.07
    Nhap
    0.07
     wholes
    0.07
    _Tag
    0.07
    お勧
    0.07
    有问题
    0.07
    赢得了
    0.07
    ግ
    0.07
    桌子上
    0.07
    работка
    0.07
    Act Density 0.001%

    No Known Activations