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

    Neuronpedia

    INDEX
    Explanations

    references to planning or guidance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.03
    2:0.29
    3:0.12
    4:0.04
    5:0.10
    6:0.04
    7:0.06
    8:0.04
    9:0.04
    10:0.06
    11:0.02
    Negative Logits
    laugh
    -2.51
     kissed
    -2.48
    isexual
    -2.41
     Zam
    -2.32
     Rouge
    -2.27
    Hug
    -2.23
     kisses
    -2.21
     abused
    -2.18
     kiss
    -2.14
    Gay
    -2.13
    POSITIVE LOGITS
     planner
    5.01
     planners
    4.80
     Planning
    4.60
     planning
    4.59
    Plan
    4.32
     plan
    3.86
     preparation
    3.73
     blueprint
    3.73
     Prepar
    3.63
     preparations
    3.59
    Act Density 0.358%

    No Known Activations