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

    Neuronpedia

    INDEX
    Explanations

    references to the city of Detroit

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Detroit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anten
    -0.72
     proxies
    -0.70
    hai
    -0.67
    acer
    -0.67
     VPN
    -0.66
     packets
    -0.64
    Ul
    -0.64
     allowances
    -0.63
    aul
    -0.63
     spoon
    -0.63
    POSITIVE LOGITS
     Detroit
    3.63
    Detroit
    3.43
     Michigan
    2.03
     Milwaukee
    1.95
     Chicago
    1.93
    Michigan
    1.92
     Oakland
    1.87
     Lansing
    1.86
    Chicago
    1.84
     Pistons
    1.82
    Act Density 0.019%

    No Known Activations