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

    Neuronpedia

    INDEX
    Explanations

    references to structured environments and training facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     institutes
    -0.14
     festivals
    -0.14
     suburbs
    -0.13
    rollo
    -0.13
     Institutes
    -0.13
    chain
    -0.13
     settlements
    -0.13
     Chains
    -0.13
    chains
    -0.13
    anko
    -0.13
    POSITIVE LOGITS
     room
    0.87
     rooms
    0.73
     Room
    0.73
    room
    0.73
    -room
    0.69
     ROOM
    0.67
    Room
    0.67
     Rooms
    0.61
    rooms
    0.60
    ROOM
    0.60
    Act Density 0.423%

    No Known Activations