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

    Neuronpedia

    INDEX
    Explanations

    phrases related to law enforcement actions, particularly those involving traffic violations and DUI incidents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     isComment
    -0.47
    waffle
    -0.47
    쨌
    -0.47
    apimachinery
    -0.46
    nictwa
    -0.46
    "])
    -0.46
    chapper
    -0.46
     prod
    -0.46
    日閲覧
    -0.46
    eira
    -0.45
    POSITIVE LOGITS
     Driving
    0.98
    Driving
    0.92
     driving
    0.87
    driving
    0.77
     Drivers
    0.68
     Highway
    0.64
     Sitten
    0.64
     Driver
    0.63
     Drive
    0.63
    Drive
    0.63
    Act Density 0.078%

    No Known Activations