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

    Neuronpedia

    INDEX
    Explanations

    words related to notable names, particularly the name "Nicolas."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Nicolas"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roach
    -0.80
    Seattle
    -0.80
    icago
    -0.79
    iley
    -0.76
    cession
    -0.76
    idding
    -0.74
    eals
    -0.74
    ships
    -0.74
    ingly
    -0.73
    ldon
    -0.71
    POSITIVE LOGITS
     Maduro
    1.10
     Nicolas
    1.03
     Cage
    0.99
    olas
    0.87
     Hollande
    0.86
     Hugo
    0.81
    Reloaded
    0.80
     Xavier
    0.78
     François
    0.76
     Sark
    0.76
    Act Density 0.019%

    No Known Activations