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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ITHUB
    -0.07
     wilt
    -0.07
     Xu
    -0.07
    冢
    -0.07
     FTP
    -0.07
     verm
    -0.06
    %，
    -0.06
    𝐔
    -0.06
     aggravated
    -0.06
    .oauth
    -0.06
    POSITIVE LOGITS
     continua
    0.07
    pectral
    0.07
    豪华
    0.07
    -than
    0.07
    未来的
    0.06
     (~
    0.06
    Colour
    0.06
    Latitude
    0.06
    𐤂
    0.06
     guessed
    0.06
    Act Density 0.002%

    No Known Activations