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

    Neuronpedia

    INDEX
    Explanations

    references to steering systems and their characteristics in vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Coder
    -0.17
    ucz
    -0.16
    olor
    -0.16
     stretch
    -0.16
    ?family
    -0.15
    urable
    -0.15
    vely
    -0.15
    slide
    -0.14
    unca
    -0.14
    mada
    -0.14
    POSITIVE LOGITS
     wheel
    0.21
    Wheel
    0.21
     Wheel
    0.21
    -wheel
    0.20
    ongyang
    0.20
     steering
    0.20
    wheel
    0.18
     Steering
    0.17
    enschaft
    0.16
    iek
    0.16
    Act Density 0.007%

    No Known Activations