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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     impact
    -0.08
     أكثر
    -0.07
     implements
    -0.07
     multiple
    -0.07
    资格
    -0.07
    表达
    -0.07
     Rank
    -0.07
     bác
    -0.07
    回归
    -0.07
    iclass
    -0.07
    POSITIVE LOGITS
    进
    0.08
     Casual
    0.07
    庸
    0.07
     Rohing
    0.07
    #"
    0.07
     afflicted
    0.06
    Ш
    0.06
    キャンペーン
    0.06
     уч
    0.06
     Caf
    0.06
    Act Density 0.001%

    No Known Activations