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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Requirements
    -0.08
    ocker
    -0.07
    _requires
    -0.07
    SplitOptions
    -0.07
    Stage
    -0.07
    迫
    -0.07
     (),↵
    -0.07
    shaft
    -0.07
     eid
    -0.07
     roles
    -0.06
    POSITIVE LOGITS
     abuses
    0.07
     raping
    0.07
    /AP
    0.07
    -liter
    0.06
    房价
    0.06
     bik
    0.06
    对应
    0.06
    橋
    0.06
    лок
    0.06
     quot
    0.06
    Act Density 0.019%

    No Known Activations