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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .room
    -0.07
    鳏
    -0.07
    \\
    -0.07
    noon
    -0.07
     unresolved
    -0.07
    工委
    -0.07
    ある
    -0.07
    这只是
    -0.07
    为了更好
    -0.06
    clude
    -0.06
    POSITIVE LOGITS
     improves
    0.07
     stiff
    0.07
    _GC
    0.07
     Peyton
    0.06
    穿着
    0.06
    _specs
    0.06
     Dates
    0.06
     "'");↵
    0.06
     코드
    0.06
    一座
    0.06
    Act Density 0.002%

    No Known Activations