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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    耻
    -0.08
    麾
    -0.08
    裾
    -0.07
    钺
    -0.07
    年轻
    -0.07
    هى
    -0.07
    戮
    -0.07
    雾
    -0.07
     rover
    -0.06
     piss
    -0.06
    POSITIVE LOGITS
    #+#+
    0.08
    _|
    0.07
    itbart
    0.07
     Nah
    0.07
     employers
    0.07
    侵占
    0.07
    決め
    0.07
    稼
    0.07
    pra
    0.07
    ￨
    0.07
    Act Density 0.001%

    No Known Activations