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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    >"+↵
    -0.08
    instanc
    -0.08
    ),
    -0.07
    ù
    -0.07
     phosph
    -0.07
    鱼类
    -0.07
    flutter
    -0.07
    	fail
    -0.07
    第三人
    -0.07
    ⴽ
    -0.07
    POSITIVE LOGITS
    мин
    0.07
    тон
    0.07
    informatics
    0.07
    .this
    0.07
     styling
    0.07
     awhile
    0.07
     little
    0.06
     לכתוב
    0.06
    (L
    0.06
    嘉
    0.06
    Act Density 0.009%

    No Known Activations