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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     toute
    -0.07
     needy
    -0.07
    小康
    -0.07
     fullfile
    -0.07
     earned
    -0.07
     disposition
    -0.07
    Coins
    -0.07
    网友
    -0.06
    早い
    -0.06
     terms
    -0.06
    POSITIVE LOGITS
    剧烈
    0.07
     ?
    0.07
     WN
    0.06
    不稳定
    0.06
    ⼦
    0.06
    Ymd
    0.06
    '})
    0.06
     Stone
    0.06
     obese
    0.06
    니
    0.06
    Act Density 0.013%

    No Known Activations