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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "world" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     international
    -0.47
     międzynarod
    -0.46
    International
    -0.41
    international
    -0.40
    Chham
    -0.40
     internationalen
    -0.40
     internazionali
    -0.40
     internacional
    -0.38
    goto
    -0.37
     иностранных
    -0.37
    POSITIVE LOGITS
     world
    2.08
    world
    2.02
     WORLD
    1.84
    WORLD
    1.81
     World
    1.80
    World
    1.79
     mundo
    1.66
     worlds
    1.59
    worlds
    1.55
    世界
    1.52
    Act Density 0.235%

    No Known Activations