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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     swapped
    -0.07
    ,)↵
    -0.07
    
    -0.07
    领
    -0.07
     ---
    -0.07
    家人
    -0.07
    �
    -0.07
     schools
    -0.07
    ---
    -0.06
     раньше
    -0.06
    POSITIVE LOGITS
     cialis
    0.07
    郿
    0.07
    bservable
    0.07
    经验丰富
    0.07
    缜
    0.07
     Femin
    0.07
    엶
    0.06
    出品
    0.06
     feminist
    0.06
    	fwrite
    0.06
    Act Density 0.069%

    No Known Activations