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

    Neuronpedia

    INDEX
    Explanations

    references to public transportation vehicles, specifically buses

    oai_token-act-pair · gpt-3.5-turbo

    references to buses and their operational details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gem
    -0.82
     piece
    -0.78
     practitioner
    -0.77
    holder
    -0.76
     holder
    -0.75
    ertation
    -0.71
     patent
    -0.71
    ener
    -0.70
    aler
    -0.69
    pec
    -0.68
    POSITIVE LOGITS
     buses
    2.81
     trucks
    2.53
     vans
    2.40
     helicopters
    2.11
     motorcycles
    1.95
     taxis
    1.89
     boats
    1.88
     airplanes
    1.86
     vehicles
    1.85
     cars
    1.84
    Act Density 0.034%

    No Known Activations