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

    Neuronpedia

    INDEX
    Explanations

    references to the word "pie"

    oai_token-act-pair · gpt-3.5-turbo

    references to "pie."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iveness
    -0.85
    spring
    -0.77
    runners
    -0.70
    sers
    -0.70
     Examiner
    -0.69
    iqueness
    -0.68
    nen
    -0.67
     EDITION
    -0.67
    angers
    -0.65
     wip
    -0.64
    POSITIVE LOGITS
     pies
    1.13
     pie
    1.11
    ced
    1.02
    Pie
    1.02
    pie
    1.01
    cing
    0.98
    MpServer
    0.95
     crust
    0.95
     Pie
    0.93
     desserts
    0.84
    Act Density 0.023%

    No Known Activations