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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    讨厌
    -0.07
    特质
    -0.07
    rw
    -0.07
    最难
    -0.07
    _inv
    -0.07
     tasar
    -0.07
    _CHAR
    -0.07
    _PLACE
    -0.07
    _bases
    -0.07
    针对性
    -0.07
    POSITIVE LOGITS
    	ERROR
    0.07
    .cor
    0.07
     Mey
    0.06
    悄
    0.06
    精通
    0.06
    -family
    0.06
    (\
    0.06
     toned
    0.06
    grid
    0.06
    国
    0.06
    Act Density 0.021%

    No Known Activations