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

    Neuronpedia

    INDEX
    Explanations

    references to the city of New York

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    milo
    -0.83
    cher
    -0.78
    ches
    -0.77
    ched
    -0.75
    vol
    -0.73
    pill
    -0.73
    olate
    -0.73
    wcsstore
    -0.72
    hig
    -0.71
    imil
    -0.71
    POSITIVE LOGITS
     City
    1.76
     State
    1.17
     Harbor
    1.14
     Cosmos
    1.08
    City
    1.08
     Jets
    1.07
     CITY
    1.07
     Mellon
    1.07
     Times
    1.05
     Giants
    1.05
    Act Density 0.042%

    No Known Activations