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
     lenker
    -0.72
     globale
    -0.70
    Testimonials
    -0.68
    GLOBAL
    -0.68
    πομπ
    -0.65
    transQ
    -0.65
    !(:
    -0.64
    ictwa
    -0.62
     Global
    -0.61
    zbęd
    -0.61
    POSITIVE LOGITS
     world
    3.61
    world
    3.16
    World
    2.60
     World
    2.54
     WORLD
    2.47
    WORLD
    2.28
    世界
    2.18
     mundo
    2.16
     worlds
    2.13
     wereld
    2.11
    Act Density 0.149%

    No Known Activations