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

    Neuronpedia

    INDEX
    Explanations

    references to traffic-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of traffic-related topics and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -1.17
    utical
    -0.83
    nai
    -0.78
    atever
    -0.78
    lain
    -0.77
    arity
    -0.77
    theless
    -0.74
     Lazarus
    -0.72
    krit
    -0.71
    thing
    -0.67
    POSITIVE LOGITS
     jams
    1.38
     congestion
    1.35
     cones
    1.02
     lanes
    1.02
     fatalities
    1.00
     calming
    0.99
     traffic
    0.99
     accidents
    0.97
     jam
    0.93
     flow
    0.93
    Act Density 0.043%

    No Known Activations