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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ╄
    -0.07
    韵
    -0.07
    	cerr
    -0.07
    ср
    -0.07
    땃
    -0.07
    走在
    -0.07
    שיא
    -0.07
    珕
    -0.06
    вен
    -0.06
    egr
    -0.06
    POSITIVE LOGITS
     chopped
    0.08
     Loose
    0.08
    网络安全
    0.07
     Jud
    0.07
    (Position
    0.07
    _ot
    0.07
    _possible
    0.07
     Things
    0.07
     ideology
    0.07
     unbelie
    0.07
    Act Density 0.001%

    No Known Activations