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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    班主任
    -0.07
     Ürün
    -0.07
     sincere
    -0.07
    );↵↵↵
    -0.07
    hel
    -0.06
    );↵↵↵↵
    -0.06
    (connection
    -0.06
    无知
    -0.06
     científ
    -0.06
     실행
    -0.06
    POSITIVE LOGITS
    收割
    0.07
    每一次
    0.07
     landscaping
    0.07
     Cement
    0.06
    	F
    0.06
    你看
    0.06
    UserProfile
    0.06
     distancing
    0.06
     Guess
    0.06
     Preferred
    0.06
    Act Density 0.010%

    No Known Activations