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

    Neuronpedia

    INDEX
    Explanations

    words related to braking mechanisms and actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to braking systems and performance in vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anto
    -0.89
    guyen
    -0.86
    iannopoulos
    -0.82
    ires
    -0.79
    atters
    -0.77
    ourning
    -0.76
    alg
    -0.75
    arez
    -0.75
    orn
    -0.73
     Serving
    -0.71
    POSITIVE LOGITS
     brake
    1.23
     brakes
    1.17
     braking
    1.15
     pedal
    1.06
     pedals
    0.92
     booster
    0.87
     levers
    0.86
     inhibitor
    0.85
     rotor
    0.84
     absor
    0.84
    Act Density 0.007%

    No Known Activations