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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "planning" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.65
    labelledby
    -0.65
    InjectAttribute
    -0.61
     مشين
    -0.59
     difesa
    -0.59
     atuação
    -0.55
    simpleType
    -0.55
    XmlRootElement
    -0.54
     colorWith
    -0.54
     dépasser
    -0.54
    POSITIVE LOGITS
     planning
    4.09
    planning
    3.60
     Planning
    3.56
    Planning
    3.48
     plan
    3.30
     PLANNING
    3.27
     plans
    3.07
     planners
    2.96
    plan
    2.92
     planner
    2.91
    Act Density 0.081%

    No Known Activations