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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    相比于
    -0.07
    쎅
    -0.07
     גיל
    -0.07
    =dict
    -0.07
     Informationen
    -0.07
    חוז
    -0.06
    בול
    -0.06
    撵
    -0.06
    有色
    -0.06
    .mul
    -0.06
    POSITIVE LOGITS
    rdf
    0.08
    廣告
    0.08
     indem
    0.07
     sanitary
    0.07
     sweeps
    0.07
    DESCRIPTION
    0.07
     speak
    0.07
    billing
    0.07
    Paragraph
    0.07
    CDF
    0.07
    Act Density 0.003%

    No Known Activations