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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝐎
    -0.07
    Resize
    -0.07
    IN
    -0.07
    ڑ
    -0.07
    /Common
    -0.07
     MAY
    -0.07
    _ENT
    -0.07
    ymax
    -0.07
    违章
    -0.07
    .Abstractions
    -0.06
    POSITIVE LOGITS
     CURL
    0.08
    	exp
    0.08
    짧
    0.07
    _safe
    0.07
     Loss
    0.07
    collectionView
    0.07
    ♣
    0.07
    chair
    0.07
     access
    0.07
    Fair
    0.07
    Act Density 0.062%

    No Known Activations