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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific location, in this case, New York City

    oai_token-act-pair · gpt-3.5-turbo

    references to New York City

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tle
    -0.96
    ibilities
    -0.91
    etsk
    -0.86
    elines
    -0.81
    rar
    -0.81
    CHAT
    -0.81
    wcsstore
    -0.80
    lyak
    -0.78
    syn
    -0.75
    ener
    -0.75
    POSITIVE LOGITS
     Council
    0.98
     District
    0.93
    scape
    0.91
     skyline
    0.90
     Opera
    0.85
     landmarks
    0.84
     Police
    0.83
     Mayor
    0.83
     streets
    0.81
     Taxi
    0.81
    Act Density 0.022%

    No Known Activations