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

    Neuronpedia

    INDEX
    Explanations

    mentions of food-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to food and its related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orp
    -0.90
     Freem
    -0.75
    acular
    -0.71
     Masonic
    -0.69
     Werewolf
    -0.69
    inct
    -0.67
     Gemini
    -0.67
     Vaughn
    -0.66
     Wink
    -0.66
     Studio
    -0.65
    POSITIVE LOGITS
    stuff
    0.98
    corn
    0.98
     eaten
    0.96
    stocks
    0.93
     nutrit
    0.92
    grain
    0.92
     sacrific
    0.88
     grains
    0.88
     crops
    0.87
    food
    0.86
    Act Density 0.034%

    No Known Activations