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

    Neuronpedia

    INDEX
    Explanations

    words related to engines and components of machinery

    oai_token-act-pair · gpt-3.5-turbo

    references to engines and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icho
    -0.81
    oslov
    -0.79
    azo
    -0.79
    atana
    -0.77
    76561
    -0.74
    laus
    -0.73
    istani
    -0.70
    ean
    -0.70
    atar
    -0.69
    chal
    -0.69
    POSITIVE LOGITS
     braking
    1.06
     powering
    1.04
     compartment
    1.00
     combustion
    1.00
     engine
    0.94
     ignition
    0.92
     horsepower
    0.92
     engines
    0.90
     turbine
    0.90
     roared
    0.89
    Act Density 0.068%

    No Known Activations