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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    力气
    -0.07
    $$
    -0.07
    yr
    -0.07
    冶炼
    -0.07
    🙊
    -0.07
    此基础上
    -0.06
    ISK
    -0.06
    unkt
    -0.06
     Wak
    -0.06
     lashes
    -0.06
    POSITIVE LOGITS
    参考
    0.07
    =response
    0.07
    unistd
    0.07
    跟我说
    0.07
    Dual
    0.07
    	username
    0.07
    城管
    0.07
    =format
    0.07
    .company
    0.07
    想找
    0.07
    Act Density 0.016%

    No Known Activations