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

    Neuronpedia

    INDEX
    Explanations

    instances of safety and interactions between vehicles and cyclists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewire
    -0.17
    ONSE
    -0.15
    ishi
    -0.14
    entes
    -0.14
    ibri
    -0.14
    .increment
    -0.14
     actionTypes
    -0.14
    sian
    -0.14
    PTY
    -0.14
    /Gate
    -0.14
    POSITIVE LOGITS
     rear
    0.22
     merge
    0.18
     behind
    0.18
    Ahead
    0.18
     Rear
    0.17
     Ahead
    0.17
    usta
    0.16
     ahead
    0.16
    hog
    0.15
     lane
    0.15
    Act Density 0.037%

    No Known Activations