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

    Neuronpedia

    INDEX
    Explanations

    technical jargon related to programming and object manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    一見
    -0.64
    urlpatterns
    -0.61
     correspondent
    -0.55
    ]='\
    -0.54
    reducible
    -0.54
     obtainable
    -0.53
     Majefty
    -0.52
     drawn
    -0.51
     realization
    -0.50
     worn
    -0.50
    POSITIVE LOGITS
     betweenstory
    0.80
     мәкал
    0.71
     Bourgoin
    0.70
     them
    0.65
     Himo
    0.65
     ویکی‌پدیا
    0.63
     متعلقه
    0.62
     cuantos
    0.61
     stället
    0.60
     Exacts
    0.59
    Act Density 0.279%

    No Known Activations