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

    Neuronpedia

    INDEX
    Explanations

    references to vehicles and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LabelTagHelper
    -0.67
     समीक्षक
    -0.57
    untura
    -0.52
    pidou
    -0.52
    пиона
    -0.51
     kasarigan
    -0.51
    SizeF
    -0.49
     Chwiliwch
    -0.48
    checkNotNull
    -0.48
     secret
    -0.47
    POSITIVE LOGITS
     vehicles
    1.00
     vehicle
    0.89
    vehicles
    0.88
     cars
    0.84
     Vehicles
    0.81
     veh
    0.79
    vehicle
    0.79
     tricycle
    0.78
     automobiles
    0.77
    Vehicles
    0.75
    Act Density 0.252%

    No Known Activations