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

    Neuronpedia

    INDEX
    Explanations

    locations within a building related to events or conflicts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rounds
    -0.72
    nir
    -0.72
    utan
    -0.72
    CHAT
    -0.68
    ï¸ı
    -0.66
    ãģĦ
    -0.65
     Marketable
    -0.62
     Uz
    -0.60
    yon
    -0.60
    OTH
    -0.59
    POSITIVE LOGITS
     doors
    1.07
     entrances
    1.06
     floor
    1.00
     entrance
    0.99
    room
    0.98
    house
    0.97
     door
    0.95
    itory
    0.94
    acle
    0.94
    keeper
    0.93
    Act Density 4.812%

    No Known Activations