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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "world."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noDo
    -0.55
     Rinse
    -0.50
    Rinse
    -0.46
    Insee
    -0.46
    atalytic
    -0.45
     Cytometry
    -0.42
     Hackney
    -0.39
     triggers
    -0.39
    TabIndex
    -0.38
     לק
    -0.38
    POSITIVE LOGITS
     world
    1.60
    World
    1.56
    world
    1.55
     World
    1.50
     WORLD
    1.46
    WORLD
    1.44
     wereld
    1.17
    orld
    1.16
     worlds
    1.16
    getWorld
    1.13
    Act Density 0.091%

    No Known Activations