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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bed
    -0.07
    .models
    -0.07
     ducks
    -0.07
     cram
    -0.07
    MinMax
    -0.07
    xfc
    -0.07
     knocking
    -0.07
     cocks
    -0.06
    HttpGet
    -0.06
    omes
    -0.06
    POSITIVE LOGITS
     dịch
    0.07
     Patriot
    0.07
    際
    0.07
     EFF
    0.07
     świat
    0.07
    类别
    0.07
     Martian
    0.07
     dzie
    0.07
    사회
    0.06
     jus
    0.06
    Act Density 0.003%

    No Known Activations