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

    Neuronpedia

    INDEX
    Explanations

    words related to engines

    oai_token-act-pair · gpt-3.5-turbo

    references to engines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laus
    -0.98
    istani
    -0.84
    atana
    -0.79
    imedia
    -0.76
    Ń·
    -0.76
    soever
    -0.76
     Childhood
    -0.75
    oslov
    -0.72
    ties
    -0.70
     Jagu
    -0.69
    POSITIVE LOGITS
     powering
    0.90
     compartment
    0.82
     braking
    0.82
     powered
    0.80
     horsepower
    0.79
     bay
    0.78
     engine
    0.78
     ignition
    0.77
     prope
    0.73
     trunk
    0.73
    Act Density 0.019%

    No Known Activations