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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    uncan
    -0.07
    党的十九
    -0.07
     touched
    -0.07
    暧
    -0.06
     sức
    -0.06
    _Selection
    -0.06
    Knight
    -0.06
     위원님
    -0.06
    ☗
    -0.06
    ✩
    -0.06
    POSITIVE LOGITS
    _free
    0.07
    .logical
    0.07
    _embedding
    0.07
     Khan
    0.07
    belie
    0.07
     Bản
    0.07
     wolves
    0.06
    虚拟
    0.06
     ub
    0.06
     dolphins
    0.06
    Act Density 0.005%

    No Known Activations