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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Dolly
    0.47
    逅
    0.41
     AV
    0.40
     DHT
    0.40
     BeautifulSoup
    0.39
     科
    0.39
     Mighty
    0.39
     Dress
    0.38
     Forge
    0.38
     Cayenne
    0.38
    POSITIVE LOGITS
    Για
    0.46
    برای
    0.39
    για
    0.37
     עבור
    0.37
    expérience
    0.36
     இனி
    0.36
    )-(
    0.34
    褒
    0.34
     για
    0.34
     embold
    0.34
    Act Density 0.000%

    No Known Activations