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

    Neuronpedia

    INDEX
    Explanations

    ingredients and quantities used in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ató
    -1.62
    iless
    -1.53
     addicted
    -1.51
    fiddle
    -1.51
     addict
    -1.48
     poverty
    -1.43
    STEM
    -1.43
    abil
    -1.42
    anta
    -1.41
    leep
    -1.40
    POSITIVE LOGITS
    º
    3.83
    ł
    3.81
    ↵↵
    3.72
    ↵↵
    3.72
    ↵
    3.72
    3.72
    <|outofrange|>
    3.72
    3.72
    ↵
    3.72
    ↵
    3.72
    Act Density 1.234%

    No Known Activations