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

    Neuronpedia

    INDEX
    Explanations

    references to road safety and traffic-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intel
    -0.13
     Boeing
    -0.13
    rail
    -0.12
    htub
    -0.12
     Marriott
    -0.12
     Robotics
    -0.12
    ckett
    -0.12
    ãĥŃãĥ¼
    -0.12
     marching
    -0.12
    ÑĤим
    -0.12
    POSITIVE LOGITS
     driving
    0.75
     Driving
    0.67
     driver
    0.65
     drivers
    0.63
    -driving
    0.61
     drive
    0.61
    Driving
    0.59
     Drive
    0.57
     Drivers
    0.57
     Driver
    0.56
    Act Density 0.930%

    No Known Activations