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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bekommen
    -0.07
    /control
    -0.07
    -Version
    -0.07
     vc
    -0.07
    歧视
    -0.07
     alto
    -0.07
    责任编辑
    -0.06
     waive
    -0.06
    �
    -0.06
    Brandon
    -0.06
    POSITIVE LOGITS
    整個
    0.07
    整个
    0.07
     Coloring
    0.07
     Specification
    0.07
    Ꭵ
    0.07
     ******************************************************************************/↵↵
    0.06
    液压
    0.06
    Abort
    0.06
     central
    0.06
    ут
    0.06
    Act Density 0.067%

    No Known Activations