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

    Neuronpedia

    INDEX
    Explanations

    terms related to food or nutrition

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dhabi
    -0.83
    ño
    -0.83
     Bots
    -0.74
     Riders
    -0.71
     Blades
    -0.70
    vu
    -0.69
    vernment
    -0.68
    âĸ¬
    -0.66
     Janeiro
    -0.65
     Saud
    -0.65
    POSITIVE LOGITS
     eaten
    1.04
     foods
    1.01
    Ingredients
    0.86
     consumed
    0.84
    paste
    0.83
     eater
    0.82
     ingested
    0.82
     fats
    0.81
     gluten
    0.80
     allergies
    0.79
    Act Density 0.039%

    No Known Activations