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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     married
    -0.08
     defend
    -0.07
    さんの
    -0.07
    ERCHANTABILITY
    -0.06
     giả
    -0.06
     phản
    -0.06
    -authored
    -0.06
     무엇
    -0.06
    character
    -0.06
    녹
    -0.06
    POSITIVE LOGITS
     doc
    0.06
    赗
    0.06
    �
    0.06
    _ct
    0.06
     Policies
    0.06
    	rect
    0.06
    إعل
    0.06
    Fun
    0.06
    functions
    0.06
    $val
    0.06
    Act Density 0.084%

    No Known Activations