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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     QAction
    -0.07
    .square
    -0.07
    tok
    -0.07
    ér
    -0.07
    畢
    -0.07
    	df
    -0.07
    yer
    -0.07
    скоп
    -0.07
    uelles
    -0.07
     dollars
    -0.06
    POSITIVE LOGITS
     ngừa
    0.07
    ۽
    0.07
     наблюда
    0.07
    对他
    0.07
    (dst
    0.06
    的优势
    0.06
    Mvc
    0.06
    有大量的
    0.06
     enhancement
    0.06
     WCS
    0.06
    Act Density 0.007%

    No Known Activations