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

    Neuronpedia

    INDEX
    Explanations

    references to pie

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instances of the word "pie."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    spring
    -0.80
    iveness
    -0.75
     Students
    -0.73
     EDITION
    -0.70
    runners
    -0.70
     Examiner
    -0.70
    nen
    -0.68
    nesses
    -0.67
    sers
    -0.66
    iqueness
    -0.64
    POSITIVE LOGITS
     pie
    1.30
     pies
    1.24
    pie
    1.09
     Pie
    0.98
    Pie
    0.96
     crust
    0.91
     desserts
    0.89
    artisan
    0.83
    ced
    0.82
     dough
    0.80
    Act Density 0.013%

    No Known Activations