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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bipolar
    -0.08
    赫
    -0.07
     calam
    -0.07
    梵
    -0.07
    by
    -0.07
     Engel
    -0.07
    違反
    -0.07
    iou
    -0.07
     우리나
    -0.07
     dato
    -0.07
    POSITIVE LOGITS
     SPA
    0.08
    썜
    0.07
    _off
    0.07
    orthand
    0.07
     Sorry
    0.07
     promotion
    0.06
    (owner
    0.06
     stripper
    0.06
    outside
    0.06
     Headers
    0.06
    Act Density 0.001%

    No Known Activations