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

    Neuronpedia

    INDEX
    Explanations

    references to different types of bikes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of bicycles and motorcycles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ringe
    -0.75
     hole
    -0.75
     layer
    -0.73
     strip
    -0.70
     job
    -0.70
     counterpart
    -0.69
     symptom
    -0.69
    area
    -0.69
     fragment
    -0.68
    pter
    -0.68
    POSITIVE LOGITS
     bikes
    2.48
     bicycles
    2.28
     motorcycles
    2.23
     shotguns
    1.87
     knives
    1.73
     rifles
    1.70
     pistols
    1.69
     guitars
    1.66
     boats
    1.62
     desks
    1.59
    Act Density 0.031%

    No Known Activations