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

    Neuronpedia

    INDEX
    Explanations

    references to different geographic locations or areas of context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arrett
    -0.80
     Raf
    -0.78
    Doug
    -0.76
    osponsors
    -0.75
    interstitial
    -0.75
     Daniels
    -0.75
     Reed
    -0.74
     Dillon
    -0.72
     Perkins
    -0.72
    rr
    -0.72
    POSITIVE LOGITS
     World
    1.18
     WORLD
    1.15
     world
    1.14
    world
    1.12
    World
    1.11
    orld
    1.05
     Universe
    1.03
     globalization
    0.98
     society
    0.96
     Worlds
    0.95
    Act Density 0.077%

    No Known Activations