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

    Neuronpedia

    INDEX
    Explanations

    expressions emphasizing connection and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cision
    -0.15
    exo
    -0.15
    ijd
    -0.14
    aque
    -0.14
    uj
    -0.13
    idea
    -0.13
    rench
    -0.13
    istros
    -0.13
    oub
    -0.13
    lier
    -0.13
    POSITIVE LOGITS
     recipe
    0.37
     ingredient
    0.34
     ingredients
    0.34
     secret
    0.30
     keys
    0.30
     Ingredients
    0.30
     formula
    0.29
    Ingredients
    0.29
     Recipe
    0.29
     Ingredient
    0.28
    Act Density 0.207%

    No Known Activations