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

    Neuronpedia

    INDEX
    Explanations

    references to sweet treats or desserts

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of desserts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hancock
    -0.75
     plur
    -0.74
     Nau
    -0.71
     Hutchinson
    -0.69
    ne
    -0.68
    inventoryQuantity
    -0.68
    sighted
    -0.67
    orne
    -0.67
    ought
    -0.67
     Caldwell
    -0.66
    POSITIVE LOGITS
    essert
    1.10
     dessert
    1.09
     desserts
    0.97
     Sparkle
    0.91
     sweets
    0.85
    oleon
    0.84
     pudding
    0.81
     decoration
    0.80
     topping
    0.80
    isine
    0.77
    Act Density 0.015%

    No Known Activations