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

    Neuronpedia

    INDEX
    Explanations

    references to cars or automobiles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    car

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olato
    -0.51
     Blitz
    -0.50
    }),
    -0.50
    yto
    -0.49
     Gottfried
    -0.49
    pena
    -0.45
    enei
    -0.45
    onde
    -0.45
     Nielsen
    -0.44
    ede
    -0.44
    POSITIVE LOGITS
     car
    1.48
     cars
    1.26
    Car
    1.24
     Car
    1.22
    car
    1.17
     Cars
    1.15
    Cars
    1.10
    cars
    1.09
     voiture
    0.96
     CARS
    0.95
    Act Density 0.015%

    No Known Activations