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

    Neuronpedia

    INDEX
    Explanations

    phrases related to plant-based diets

    oai_token-act-pair · gpt-3.5-turbo

    references to plants, especially in the context of production or dietary significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.85
    ROR
    -0.78
    pires
    -0.78
    yip
    -0.75
    laus
    -0.72
    olulu
    -0.68
    vernment
    -0.68
    gettable
    -0.67
     reluct
    -0.67
    alty
    -0.66
    POSITIVE LOGITS
    ronics
    1.04
     plants
    0.90
     plant
    0.87
    plant
    0.85
    overs
    0.77
    yards
    0.74
    yard
    0.74
    uve
    0.74
     farms
    0.73
    arded
    0.72
    Act Density 0.014%

    No Known Activations