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

    Neuronpedia

    INDEX
    Explanations

    recipes and food related phrases

    oai_token-act-pair · gpt-3.5-turbo

    expressions of enthusiasm and positive sentiment towards food and recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RSA
    -0.86
     Gamergate
    -0.81
    aspers
    -0.79
     unmanned
    -0.78
     jurisd
    -0.77
     cybersecurity
    -0.76
     Oswald
    -0.75
     arbitration
    -0.74
     Assange
    -0.74
     EEG
    -0.73
    POSITIVE LOGITS
     creamy
    1.20
    Ingredients
    1.14
     veggies
    1.14
     Ingredients
    1.14
     gluten
    1.11
     Vegan
    1.08
     freezer
    1.08
     Cooking
    1.07
     delicious
    1.07
    Recipe
    1.07
    Act Density 0.973%

    No Known Activations