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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     understands
    -0.08
    ʿ
    -0.08
     Experimental
    -0.07
    独
    -0.07
     Dh
    -0.07
     ethn
    -0.07
    自动驾驶
    -0.07
     mitochondrial
    -0.07
    Employ
    -0.07
     explanations
    -0.07
    POSITIVE LOGITS
    㶲
    0.08
    徐州
    0.07
    澪
    0.07
    ﯷ
    0.07
    魈
    0.07
    (script
    0.07
    깜
    0.07
    bilit
    0.07
     soda
    0.07
    结束后
    0.07
    Act Density 0.062%

    No Known Activations