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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ejs
    -0.07
    pay
    -0.07
    茗
    -0.07
    采暖
    -0.07
    珍惜
    -0.07
    Seller
    -0.06
     accepts
    -0.06
    十佳
    -0.06
    优秀
    -0.06
    წ
    -0.06
    POSITIVE LOGITS
     Kısa
    0.07
     lake
    0.07
    高位
    0.07
    :"↵
    0.07
    ье
    0.06
    :"#
    0.06
     naval
    0.06
     הל
    0.06
     saint
    0.06
     הא
    0.06
    Act Density 0.038%

    No Known Activations