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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with weight loss and health-related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odon
    -0.16
    åĽ°
    -0.15
    rawn
    -0.15
    ldr
    -0.15
    omed
    -0.14
    bert
    -0.14
    /vector
    -0.14
    ibri
    -0.14
    ardi
    -0.13
    CharCode
    -0.13
    POSITIVE LOGITS
     ingredients
    0.29
     Ingredients
    0.28
     ingredient
    0.27
    Ingredients
    0.26
     formula
    0.26
    ingredients
    0.26
    formula
    0.23
    Claims
    0.22
     Claims
    0.21
     Ingredient
    0.21
    Act Density 0.021%

    No Known Activations