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

    Neuronpedia

    INDEX
    Explanations

    mentions of different types of sugars

    oai_token-act-pair · gpt-3.5-turbo

    references to sugar and its various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersen
    -0.75
    naires
    -0.72
     Tsarnaev
    -0.70
    ļé
    -0.70
    naire
    -0.69
    atche
    -0.68
    acular
    -0.68
     FML
    -0.66
    orate
    -0.65
     Stockholm
    -0.64
    POSITIVE LOGITS
     cane
    1.35
     beet
    1.15
     syrup
    1.14
    cone
    0.94
    cube
    0.92
     maple
    0.89
    coat
    0.88
     daddy
    0.88
    sweet
    0.86
    ptive
    0.83
    Act Density 0.052%

    No Known Activations