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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     rm
    -0.07
     jade
    -0.07
     productivity
    -0.07
     lessen
    -0.07
    .getResult
    -0.07
    (reader
    -0.07
    watch
    -0.07
    east
    -0.07
     jedem
    -0.07
    Replacing
    -0.07
    POSITIVE LOGITS
    OfSize
    0.07
    낍
    0.07
    ឋ
    0.07
    푀
    0.07
    ┕
    0.07
    作息
    0.06
    穙
    0.06
    脶
    0.06
    碏
    0.06
    fläche
    0.06
    Act Density 0.002%

    No Known Activations