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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _BEGIN
    -0.07
    浓浓的
    -0.07
     €
    -0.07
    赞
    -0.07
    _roll
    -0.07
    疾
    -0.07
    Linux
    -0.07
    挺
    -0.07
     Restaurant
    -0.07
    _dependencies
    -0.07
    POSITIVE LOGITS
     LENGTH
    0.07
    perms
    0.07
    ۦ
    0.06
    私下
    0.06
    	 
↵
    0.06
    鞨
    0.06
     FontWeight
    0.06
    erdale
    0.06
    们
    0.06
    没有必要
    0.06
    Act Density 0.002%

    No Known Activations