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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    汁
    -0.07
    mo
    -0.07
    쎗
    -0.07
    ben
    -0.07
    ảy
    -0.07
    比赛中
    -0.07
    的就是
    -0.07
    쟝
    -0.06
     }])↵
    -0.06
    면
    -0.06
    POSITIVE LOGITS
    _plot
    0.07
     glor
    0.07
    _u
    0.07
     Port
    0.07
     regulatory
    0.07
    STEM
    0.07
    Chart
    0.06
     UM
    0.06
    昭
    0.06
    二次
    0.06
    Act Density 0.033%

    No Known Activations