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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Champion
    0.63
     and
    0.61
     Recognizing
    0.59
     by
    0.57
     COVID
    0.57
     headquartered
    0.57
    忠
    0.55
     recognizes
    0.55
     Certified
    0.54
     Clause
    0.54
    POSITIVE LOGITS
     cappuccino
    0.78
     przysz
    0.72
    delicious
    0.71
    credibly
    0.71
    tired
    0.71
    unat
    0.70
     bencana
    0.69
    😋
    0.68
     indah
    0.68
     sava
    0.67
    Act Density 0.002%

    No Known Activations