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

    Neuronpedia

    INDEX
    Explanations

    references to automobiles or vehicles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aido
    -0.86
    bread
    -0.80
    iaries
    -0.71
    artz
    -0.70
    gements
    -0.70
    ews
    -0.69
    kai
    -0.68
    yo
    -0.68
     Brother
    -0.67
    awar
    -0.65
    POSITIVE LOGITS
     vehicle
    1.04
     vehicles
    0.92
    veh
    0.91
    Veh
    0.89
     dealership
    0.85
    lane
    0.85
     parked
    0.83
    chairs
    0.80
     Vehicle
    0.79
     cars
    0.78
    Act Density 0.014%

    No Known Activations