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

    Neuronpedia

    INDEX
    Explanations

    references to doors and their related context in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucci
    -0.17
    inerary
    -0.16
    ency
    -0.15
    emia
    -0.15
     æĸ
    -0.14
    ConnectionFactory
    -0.14
    ching
    -0.14
    mons
    -0.14
    ırak
    -0.14
    eum
    -0.14
    POSITIVE LOGITS
    -door
    0.21
    ways
    0.16
    çİĦ
    0.16
    /window
    0.15
    house
    0.15
    keeper
    0.15
     resil
    0.15
    nd
    0.15
    /Gate
    0.15
    aleigh
    0.15
    Act Density 0.039%

    No Known Activations