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

    Neuronpedia

    INDEX
    Explanations

    mentions of vegetables

    oai_token-act-pair · gpt-3.5-turbo

    references to vegetables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ORN
    -0.78
    interstitial
    -0.76
    oning
    -0.75
    administ
    -0.75
    dinand
    -0.71
    elected
    -0.71
    DOS
    -0.71
    raped
    -0.70
    office
    -0.69
    raints
    -0.68
    POSITIVE LOGITS
     vegetables
    1.04
     vegetable
    0.94
     soup
    0.92
     garden
    0.88
     veggies
    0.86
     juice
    0.84
     peel
    0.84
     Soup
    0.83
     salad
    0.82
     spinach
    0.82
    Act Density 0.014%

    No Known Activations