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

    Neuronpedia

    INDEX
    Explanations

    people's names

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those named David, within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imately
    -0.75
    ï¸ı
    -0.71
     broom
    -0.71
    vous
    -0.70
    yip
    -0.69
    ashtra
    -0.63
     gem
    -0.62
     LEDs
    -0.60
     Petr
    -0.59
     yarn
    -0.57
    POSITIVE LOGITS
    Marsh
    0.65
    canon
    0.65
    mberg
    0.64
    ukes
    0.63
    asley
    0.63
     Kelley
    0.62
    insky
    0.62
    mann
    0.62
    oyer
    0.62
     Johnston
    0.61
    Act Density 0.104%

    No Known Activations