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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "world" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UserScript
    -0.70
     Baillargeon
    -0.68
     propOrder
    -0.68
    ngdoc
    -0.67
     AttributeSet
    -0.67
    SourceChecksum
    -0.67
    Personensuche
    -0.63
    adpleegd
    -0.63
     AppDelegate
    -0.63
    ConstraintMaker
    -0.63
    POSITIVE LOGITS
     World
    4.70
    World
    4.36
     WORLD
    3.80
    world
    3.60
     world
    3.55
    WORLD
    3.54
     Worlds
    2.59
     Welt
    2.57
    世界
    2.56
    orld
    2.40
    Act Density 0.054%

    No Known Activations