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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    لی
    0.73
     पक्षा
    0.73
     झालं
    0.72
     дальнейшем
    0.71
    ousine
    0.70
     bolts
    0.68
    ologne
    0.68
    那样
    0.64
    ஸ்ட
    0.64
    arettes
    0.64
    POSITIVE LOGITS
    it
    0.87
    ⌣
    0.85
     contenders
    0.80
    negl
    0.75
     contender
    0.75
     Relig
    0.75
     extrav
    0.73
     interstitiis
    0.71
     sensit
    0.71
     `-
    0.70
    Act Density 0.002%

    No Known Activations