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

    Neuronpedia

    INDEX
    Explanations

    ingredients or food items, particularly garlic

    oai_token-act-pair · gpt-3.5-turbo

    references to garlic in food descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Franch
    -0.75
     Atlanta
    -0.72
     Ferr
    -0.70
    enture
    -0.69
     Phillips
    -0.67
     Canary
    -0.65
     Baton
    -0.64
     Lev
    -0.63
     Lv
    -0.62
     Normandy
    -0.62
    POSITIVE LOGITS
    ":"/
    0.81
    UTERS
    0.73
    API
    0.71
    shire
    0.71
    MET
    0.70
    FORE
    0.70
    pecially
    0.69
    finder
    0.69
    LEASE
    0.69
    ById
    0.68
    Act Density 0.000%

    No Known Activations