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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to food and nutritional topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =$?
    -0.67
     Pfund
    -0.60
     Skyscanner
    -0.54
    withIdentifier
    -0.53
    posedge
    -0.52
     desem
    -0.52
     Kline
    -0.51
     fleuve
    -0.50
    trise
    -0.50
     câte
    -0.50
    POSITIVE LOGITS
     food
    0.93
    Food
    0.86
     Food
    0.85
    food
    0.85
     FOOD
    0.76
    FOOD
    0.76
    stuff
    0.74
     foods
    0.73
    makanan
    0.71
    Foods
    0.68
    Act Density 0.149%

    No Known Activations