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

    Neuronpedia

    INDEX
    Explanations

    locations within a building

    oai_token-act-pair · gpt-3.5-turbo

    locations and spaces within various settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arget
    -0.67
    omorphic
    -0.64
    nesota
    -0.62
    è¦ļéĨĴ
    -0.61
    alin
    -0.61
    merce
    -0.60
    ãĥĩ
    -0.60
    ozy
    -0.60
    osate
    -0.60
    usat
    -0.59
    POSITIVE LOGITS
     hallway
    1.15
     overlooking
    1.13
     doorway
    1.11
     restroom
    1.04
    tyard
    1.04
     downstairs
    1.03
     aisle
    1.02
     toilets
    1.01
     upstairs
    1.01
     balcony
    0.99
    Act Density 0.176%

    No Known Activations