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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    沂
    -0.08
    ätz
    -0.07
    貌
    -0.07
    也要
    -0.07
    והר
    -0.07
    STALL
    -0.07
    oge
    -0.07
    勇气
    -0.07
    곯
    -0.07
    ervas
    -0.07
    POSITIVE LOGITS
    period
    0.08
     []
↵
↵
    0.07
    	function
    0.07
    енная
    0.07
    �
    0.07
    tdown
    0.07
    bing
    0.07
    death
    0.07
    cr
    0.07
     expires
    0.07
    Act Density 0.002%

    No Known Activations