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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Scanner
    -0.07
     sapi
    -0.07
     grille
    -0.07
     perg
    -0.07
    (d
    -0.07
     �
    -0.06
    _Source
    -0.06
     Fowler
    -0.06
     Raq
    -0.06
    —for
    -0.06
    POSITIVE LOGITS
    雪
    0.08
     literals
    0.08
     shootings
    0.07
    	list
    0.07
     Plant
    0.07
     orchestra
    0.07
    孙悟空
    0.07
    猜
    0.07
    ód
    0.07
    丢
    0.06
    Act Density 0.047%

    No Known Activations