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

    Neuronpedia

    INDEX
    Explanations

    cooking-related actions and ingredients in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    baking ingredients and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bespoke
    -0.45
    gemeester
    -0.45
     nuanced
    -0.44
     digress
    -0.42
    ldorf
    -0.40
    ipal
    -0.39
    :+:
    -0.39
     fein
    -0.39
     Aside
    -0.39
     fit
    -0.39
    POSITIVE LOGITS
     pleaſure
    0.61
     Jefus
    0.57
    şört
    0.51
     bonté
    0.50
     ſeveral
    0.49
     myſelf
    0.49
     daß
    0.45
     muß
    0.44
    harapkan
    0.44
     Majefty
    0.44
    Act Density 0.016%

    No Known Activations