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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "world" or "global" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Xie
    -0.88
     Ryanair
    -0.87
     للاسماء
    -0.86
     Notary
    -0.84
     Mortar
    -0.82
     desta
    -0.79
     Knudsen
    -0.79
     Pilate
    -0.78
     Amtrak
    -0.78
     Lecturer
    -0.77
    POSITIVE LOGITS
     World
    1.56
     world
    1.51
     WORLD
    1.44
    World
    1.34
    world
    1.26
     Worlds
    1.26
    WORLD
    1.26
    orld
    1.23
    Worlds
    1.22
     worlds
    1.22
    Act Density 0.043%

    No Known Activations