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

    Neuronpedia

    INDEX
    Explanations

    locations, particularly the city of Amsterdam

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ineligible
    -0.70
     eligible
    -0.67
     fielded
    -0.66
    oyal
    -0.64
    corn
    -0.62
    ue
    -0.62
     Darrell
    -0.61
     Weaver
    -0.61
     FG
    -0.61
    attribute
    -0.61
    POSITIVE LOGITS
     Bangkok
    2.40
     Mumbai
    2.35
     Jakarta
    2.29
     Frankfurt
    2.26
     Budapest
    2.25
     Manila
    2.25
     Stockholm
    2.22
     Amsterdam
    2.19
     Istanbul
    2.18
     Prague
    2.15
    Act Density 0.035%

    No Known Activations