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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     disintegration
    1.09
     obscured
    1.02
    taining
    1.00
     sucker
    0.97
    body
    0.97
     undermine
    0.96
    😣
    0.96
     Pearson
    0.95
    💐
    0.95
    ulate
    0.94
    POSITIVE LOGITS
    carouselExample
    0.93
    accès
    0.92
    ීය
    0.91
     sería
    0.89
     inicialmente
    0.88
     жители
    0.88
    originals
    0.86
    )}`;
    0.86
     mieszkańców
    0.85
     ünlü
    0.83
    Act Density 0.000%

    No Known Activations