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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.59
    GIVEREF
    -0.58
     boyfriend
    -0.52
     jeans
    -0.50
    InSection
    -0.47
     curé
    -0.47
     Supermarket
    -0.45
    WriteTagHelper
    -0.45
     girlfriend
    -0.45
    θρω
    -0.45
    POSITIVE LOGITS
     palace
    1.07
     Palace
    0.93
     imperial
    0.89
     court
    0.87
     royal
    0.84
    Palace
    0.83
    palace
    0.79
     Imperial
    0.76
     courtier
    0.75
     courtiers
    0.73
    Act Density 0.295%

    No Known Activations