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

    Neuronpedia

    INDEX
    Explanations

    references to measurements or distances, specifically involving yards

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements related to yards or yardage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Continental
    -0.67
     unic
    -0.63
     shock
    -0.63
     powers
    -0.60
     poison
    -0.59
     neurot
    -0.58
     cash
    -0.57
     electronic
    -0.57
     scams
    -0.57
     democracy
    -0.56
    POSITIVE LOGITS
    yard
    4.70
    yards
    3.44
     yard
    2.10
     Yard
    1.87
     Yards
    1.67
     yards
    1.58
    wright
    1.23
    acre
    1.11
    wreck
    1.08
    builders
    1.05
    Act Density 0.017%

    No Known Activations