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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "steer" and related words associated with guiding or directing

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to direction and guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ropolitan
    -0.79
    bs
    -0.74
     Leban
    -0.70
    ombies
    -0.68
    ones
    -0.67
    enegger
    -0.67
    ocaust
    -0.66
     Corpus
    -0.65
    urity
    -0.65
    ocalyptic
    -0.65
    POSITIVE LOGITS
     steer
    1.08
     steered
    1.01
    wheel
    0.99
     steering
    0.85
    wagon
    0.81
     toward
    0.80
    posts
    0.79
     wheel
    0.77
    chair
    0.77
     towards
    0.76
    Act Density 0.016%

    No Known Activations