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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities denoting large amounts or groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities of people or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Silence
    -0.73
    odox
    -0.69
     Carnage
    -0.68
     Finder
    -0.67
     Curious
    -0.67
     Prov
    -0.66
    cade
    -0.66
     Cyn
    -0.65
     Selection
    -0.64
     Trader
    -0.64
    POSITIVE LOGITS
     pounds
    0.95
     dollars
    0.91
    ourcing
    0.70
     lbs
    0.69
     gallons
    0.69
    lbs
    0.68
    ourced
    0.68
     kilograms
    0.68
    dollar
    0.68
    uid
    0.66
    Act Density 0.089%

    No Known Activations