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

    Neuronpedia

    INDEX
    Explanations

    terms related to traffic laws and driving behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aronder
    -0.51
     tủ
    -0.50
    MongoClient
    -0.50
    kowych
    -0.50
     Living
    -0.49
     autorytatywna
    -0.49
    Living
    -0.48
    цездатний
    -0.47
    fvar
    -0.47
     geslacht
    -0.47
    POSITIVE LOGITS
     roadway
    0.93
     traffic
    0.89
     road
    0.85
     pedestrians
    0.85
     highway
    0.82
     drivers
    0.76
     motorists
    0.75
     motorist
    0.75
     Highway
    0.74
    Traffic
    0.74
    Act Density 0.385%

    No Known Activations