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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    names of geographic locations or regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.84
    elson
    -0.82
    stanbul
    -0.77
    addafi
    -0.76
    andr
    -0.75
    agos
    -0.75
    aturation
    -0.74
    ogun
    -0.73
    oÄŁan
    -0.73
    iggs
    -0.72
    POSITIVE LOGITS
     Sussex
    1.32
     County
    1.15
     Essex
    1.15
     Borough
    1.10
     Somerset
    1.08
     Surrey
    1.00
     Middles
    1.00
     Glou
    0.97
     Spit
    0.96
     Riverside
    0.95
    Act Density 0.011%

    No Known Activations