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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    commission
    -0.08
     exemption
    -0.07
     unzip
    -0.07
     mods
    -0.07
    一周
    -0.07
     Dissertation
    -0.07
    -President
    -0.07
     Twenty
    -0.07
    𫓧
    -0.07
    _DR
    -0.07
    POSITIVE LOGITS
    [train
    0.07
     thất
    0.07
    Ụ
    0.07
    埌
    0.07
    orrent
    0.07
    ml
    0.07
    いで
    0.06
    凭证
    0.06
    企业文化
    0.06
    cha
    0.06
    Act Density 0.032%

    No Known Activations