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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "chocolate."

    oai_token-act-pair · gpt-3.5-turbo

    references to chocolate and related confections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kus
    -0.82
    WARD
    -0.79
    Filename
    -0.75
    ership
    -0.74
    ayson
    -0.73
    aday
    -0.72
    ctive
    -0.70
    igate
    -0.67
    jury
    -0.67
    ports
    -0.65
    POSITIVE LOGITS
     pudding
    0.97
     cake
    0.96
     chip
    0.92
    anut
    0.91
     cane
    0.89
     butter
    0.88
     syrup
    0.87
     sauce
    0.87
     cakes
    0.86
     flavored
    0.84
    Act Density 0.037%

    No Known Activations