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

    Neuronpedia

    INDEX
    Explanations

    the word "dessert"

    oai_token-act-pair · gpt-4-turbo

    references to desserts

    oai_token-act-pair · gpt-3.5-turbo

    references to desserts and sweet dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lev
    -0.84
    inel
    -0.72
     plur
    -0.71
    aird
    -0.71
    orne
    -0.70
    uld
    -0.67
     Hancock
    -0.67
    inventoryQuantity
    -0.66
    uilt
    -0.64
     Vest
    -0.63
    POSITIVE LOGITS
     pudding
    1.13
     dessert
    1.04
    essert
    1.00
     desserts
    0.98
     sweets
    0.84
     Sparkle
    0.84
     cake
    0.83
    oleon
    0.82
    cake
    0.80
    issance
    0.79
    Act Density 0.014%

    No Known Activations