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

    Neuronpedia

    INDEX
    Explanations

    locations and settings

    oai_token-act-pair · gpt-3.5-turbo

    locations and places where events occur

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adders
    -0.90
     Architects
    -0.75
     Empires
    -0.73
     Orders
    -0.73
    casts
    -0.72
     Clubs
    -0.72
     Plans
    -0.71
     Acts
    -0.70
     ACTIONS
    -0.69
     Laws
    -0.69
    POSITIVE LOGITS
     frequ
    1.18
     overlooking
    1.07
     staffed
    1.04
     owned
    1.04
     nearby
    1.01
     situated
    1.01
     near
    1.01
     littered
    1.00
     belonging
    1.00
     guarded
    0.98
    Act Density 0.226%

    No Known Activations