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

    Neuronpedia

    INDEX
    Explanations

    references to "world" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ryanair
    -0.92
     Notary
    -0.82
    Xie
    -0.81
     Knudsen
    -0.81
     desta
    -0.81
     Amtrak
    -0.80
    Amos
    -0.80
     Cottages
    -0.79
     للاسماء
    -0.78
     Mortar
    -0.78
    POSITIVE LOGITS
     World
    1.67
     world
    1.62
     WORLD
    1.54
    World
    1.47
    world
    1.39
    WORLD
    1.33
     Worlds
    1.32
     worlds
    1.30
    Worlds
    1.29
    orld
    1.29
    Act Density 0.050%

    No Known Activations