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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    בק
    -0.08
    起步
    -0.07
    按规定
    -0.07
    Done
    -0.07
    不错的
    -0.07
    abelle
    -0.07
    売れ
    -0.06
    jący
    -0.06
    	go
    -0.06
    ULER
    -0.06
    POSITIVE LOGITS
     Attribution
    0.06
    _people
    0.06
    -option
    0.06
    喟
    0.06
    atrib
    0.06
    !');↵
    0.06
     clones
    0.06
    庆典
    0.06
     Liberation
    0.06
    黨
    0.06
    Act Density 0.001%

    No Known Activations