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

    Neuronpedia

    INDEX
    Explanations

    references to major cities or significant landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĪÙģÙĬ
    -0.14
    ouis
    -0.13
     domestically
    -0.13
    raith
    -0.13
    elves
    -0.13
    ær
    -0.13
     Domestic
    -0.13
    ži
    -0.13
    .Dom
    -0.13
     nationwide
    -0.13
    POSITIVE LOGITS
     world
    0.74
    ä¸ĸçķĮ
    0.61
    world
    0.58
    -world
    0.57
     World
    0.55
    _world
    0.55
     WORLD
    0.53
    World
    0.52
     mundo
    0.50
     ä¸ĸçķĮ
    0.50
    Act Density 0.236%

    No Known Activations