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

    Neuronpedia

    INDEX
    Explanations

    numerical values representing years or time periods

    oai_token-act-pair · gpt-3.5-turbo

    numerical data relating to historical timeframes and archaeological findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierrez
    -0.66
    lycer
    -0.65
    itent
    -0.60
     accomplishment
    -0.60
     undercover
    -0.59
     workload
    -0.59
     brakes
    -0.59
     vetting
    -0.58
     conduc
    -0.58
     intimidation
    -0.57
    POSITIVE LOGITS
     millennia
    1.28
    century
    1.26
     millennium
    1.16
    million
    1.10
    Pg
    1.09
     BCE
    1.06
     000
    1.03
     centuries
    1.02
    billion
    1.00
    500
    0.99
    Act Density 0.062%

    No Known Activations