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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ered
    -0.79
     overc
    -0.77
    aches
    -0.75
     sear
    -0.73
    cyclopedia
    -0.71
     grilled
    -0.70
    esy
    -0.68
     franc
    -0.68
    eer
    -0.68
    uration
    -0.67
    POSITIVE LOGITS
     DeL
    0.80
    ajor
    0.76
    asar
    0.75
     Lot
    0.74
    é¾įåĸļ士
    0.72
     Buchanan
    0.70
     Bee
    0.68
    TPPStreamerBot
    0.67
    itism
    0.67
     Quin
    0.66
    Act Density 0.034%

    No Known Activations