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

    Neuronpedia

    INDEX
    Explanations

    references to the action of cooking

    oai_token-act-pair · gpt-3.5-turbo

    references to cooking and food preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venants
    -0.76
    umbn
    -0.74
    emale
    -0.72
    ertodd
    -0.70
    idas
    -0.69
    orporated
    -0.69
    orb
    -0.68
    hovah
    -0.66
    onnaissance
    -0.66
     Baghd
    -0.64
    POSITIVE LOGITS
    stall
    0.92
     cooks
    0.92
    Recipe
    0.90
     cook
    0.89
    cook
    0.87
     stove
    0.87
    Cook
    0.87
    books
    0.85
     fry
    0.83
     cooking
    0.82
    Act Density 0.017%

    No Known Activations