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

    Neuronpedia

    INDEX
    Explanations

    food-related terms, particularly different types of food items

    oai_token-act-pair · gpt-3.5-turbo

    mentions of food and dining-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ability
    -0.80
    SPONSORED
    -0.68
     Offic
    -0.66
    razil
    -0.64
    Ident
    -0.64
     Doctrine
    -0.64
     Universities
    -0.63
    Specific
    -0.63
     Citizens
    -0.62
    Function
    -0.62
    POSITIVE LOGITS
    cake
    0.93
     potato
    0.85
     popcorn
    0.85
    uity
    0.84
     pies
    0.81
     cake
    0.80
    bowl
    0.80
     soup
    0.79
    pipe
    0.78
    hoe
    0.77
    Act Density 0.266%

    No Known Activations