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

    Neuronpedia

    INDEX
    Explanations

    phrases related to traffic safety and the effects of distractions on driving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urma
    -0.17
    anim
    -0.17
    lt
    -0.14
    _formats
    -0.14
     pian
    -0.13
    /Gate
    -0.13
    iÄĻ
    -0.13
    .LookAndFeel
    -0.13
    agus
    -0.13
    oga
    -0.13
    POSITIVE LOGITS
     distracted
    0.36
     distraction
    0.32
     distractions
    0.30
     driver
    0.28
     driving
    0.26
     distract
    0.26
     texting
    0.25
     drivers
    0.25
    -driver
    0.25
     Driving
    0.24
    Act Density 0.072%

    No Known Activations