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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "pizza."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of pizza

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hips
    -0.83
    Thom
    -0.82
    draw
    -0.76
    track
    -0.76
    itud
    -0.73
    ivities
    -0.70
    say
    -0.69
    tenance
    -0.69
    nings
    -0.69
    iveness
    -0.69
    POSITIVE LOGITS
     dough
    1.12
     oven
    1.08
     crust
    1.00
    ocalypse
    0.98
     pies
    0.93
     pizza
    0.92
     delivery
    0.89
     Dough
    0.89
    isine
    0.86
     topping
    0.86
    Act Density 0.014%

    No Known Activations