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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    拉升
    -0.08
     canyon
    -0.07
     creepy
    -0.07
     responseBody
    -0.07
    知乎
    -0.07
     ThreadPool
    -0.07
     corporation
    -0.07
    顶部
    -0.07
    好奇心
    -0.07
     hood
    -0.07
    POSITIVE LOGITS
    �
    0.06
     Juan
    0.06
     Mouse
    0.06
     Пет
    0.06
    这样的
    0.06
    ład
    0.06
    庶
    0.06
    Trans
    0.06
    """),↵
    0.06
    革
    0.06
    Act Density 0.455%

    No Known Activations