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

    Neuronpedia

    INDEX
    Explanations

    locations, specifically the city of Mumbai

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city Mumbai

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minist
    -0.77
    book
    -0.76
    redo
    -0.75
    cellent
    -0.74
    isner
    -0.73
    lic
    -0.73
    rd
    -0.73
    itent
    -0.70
    lished
    -0.69
    bread
    -0.69
    POSITIVE LOGITS
     Lumpur
    1.08
    umbai
    0.83
     Express
    0.80
     Hotel
    0.79
     Hilton
    0.78
     mosqu
    0.74
     Metropolitan
    0.73
     Fashion
    0.70
     Airways
    0.69
     Indians
    0.69
    Act Density 0.011%

    No Known Activations