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

    Neuronpedia

    INDEX
    Explanations

    names of well-known individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to well-known or prominent individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    requently
    -0.76
    othy
    -0.75
    yrinth
    -0.74
    irth
    -0.69
    iaries
    -0.69
     Thoughts
    -0.68
     rapt
    -0.67
     Forestry
    -0.66
    imar
    -0.65
    sectional
    -0.65
    POSITIVE LOGITS
    lier
    0.99
    paces
    0.85
     brands
    0.84
    brand
    0.81
     contender
    0.76
    æ©
    0.76
    plates
    0.76
    hood
    0.75
     newcomer
    0.74
     contenders
    0.73
    Act Density 0.024%

    No Known Activations