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

    Neuronpedia

    INDEX
    Explanations

    references to vehicles and related incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Buses
    -0.60
     Trucks
    -0.59
     Buses
    -0.57
     Driving
    -0.55
     Trains
    -0.55
     motos
    -0.53
     Trucking
    -0.52
     Motorcycles
    -0.51
    Cycling
    -0.50
    Trains
    -0.50
    POSITIVE LOGITS
     vehicle
    1.54
    vehicle
    1.21
     car
    1.16
     vehículo
    1.01
     vehicles
    0.99
     véhicule
    0.98
     VEHICLE
    0.84
    Vehicle
    0.82
     veículo
    0.82
     veh
    0.82
    Act Density 0.305%

    No Known Activations