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

    Neuronpedia

    INDEX
    Explanations

    words related to traffic conditions and driving violations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to traffic laws and incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -1.06
    sonian
    -0.95
    DragonMagazine
    -0.90
    aceutical
    -0.80
    pha
    -0.78
    theless
    -0.77
    pora
    -0.77
    ormons
    -0.76
    ormon
    -0.75
    Tea
    -0.73
    POSITIVE LOGITS
     motorists
    1.07
     drivers
    1.02
     bicycl
    0.99
     cars
    0.96
     traffic
    0.95
     err
    0.94
     cyclists
    0.92
     motorcycles
    0.90
     Drivers
    0.90
     bikes
    0.89
    Act Density 0.221%

    No Known Activations