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

    Neuronpedia

    INDEX
    Explanations

    keywords related to driving, especially actions and scenarios involving driving

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "driving" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.83
     Seym
    -0.81
     Lum
    -0.75
    ereo
    -0.74
    tle
    -0.72
    ertain
    -0.70
    achu
    -0.69
    ellen
    -0.69
    umbn
    -0.68
    utical
    -0.67
    POSITIVE LOGITS
    wheel
    1.06
    bike
    0.94
    train
    0.92
    driving
    0.89
    boats
    0.88
     away
    0.85
    whe
    0.84
     driving
    0.83
    boat
    0.80
    ways
    0.79
    Act Density 0.038%

    No Known Activations