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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .bc
    -0.08
    füh
    -0.07
     blij
    -0.07
    chte
    -0.07
    沼
    -0.06
     gemacht
    -0.06
    очный
    -0.06
     thưởng
    -0.06
     tal
    -0.06
    鬶
    -0.06
    POSITIVE LOGITS
     LENGTH
    0.07
    /mysql
    0.07
     misogyn
    0.07
     successive
    0.07
    /new
    0.06
    上级
    0.06
     kitten
    0.06
     attained
    0.06
    身心
    0.06
    感官
    0.06
    Act Density 0.014%

    No Known Activations