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

    Neuronpedia

    INDEX
    Explanations

    food-related descriptions with elements of being "topped with" various ingredients

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "topped" or variations of it, indicating layering or adding on in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otive
    -0.70
    cci
    -0.68
     Infinite
    -0.65
     laborers
    -0.64
     Village
    -0.64
    agents
    -0.62
     Lak
    -0.62
    Import
    -0.61
    ivid
    -0.59
    æ©Ł
    -0.59
    POSITIVE LOGITS
    mast
    0.91
     topping
    0.90
    pins
    0.86
    pin
    0.82
    OGR
    0.78
    azo
    0.75
    deck
    0.75
    cream
    0.75
    ackets
    0.73
    ographically
    0.73
    Act Density 0.024%

    No Known Activations