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

    Neuronpedia

    INDEX
    Explanations

    content related to cooking recipes

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory phrases related to cooking or food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     divest
    -0.84
     broadcasting
    -0.83
     arbitration
    -0.81
     arbit
    -0.81
     probation
    -0.81
     manned
    -0.80
     renegoti
    -0.79
     corruption
    -0.79
     patrols
    -0.77
     torped
    -0.77
    POSITIVE LOGITS
    Ingredients
    1.82
    Recipe
    1.68
    Nut
    1.40
     Ingredients
    1.22
    Materials
    1.20
    Instruct
    1.17
    Anyway
    1.13
    Rated
    1.12
     Recipe
    1.12
    Easy
    1.12
    Act Density 0.312%

    No Known Activations