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

    Neuronpedia

    INDEX
    Explanations

    dates and Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    numerical dates or references that are formatted with commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     expansions
    -0.91
     detectors
    -0.76
     boosters
    -0.71
     predec
    -0.71
     corridors
    -0.65
     fossils
    -0.65
     expansion
    -0.61
     conqu
    -0.61
     successors
    -0.60
     connections
    -0.59
    POSITIVE LOGITS
     2017
    1.00
     2016
    0.96
     2015
    0.95
     2014
    0.93
    000
    0.89
     2018
    0.87
     2013
    0.84
     2012
    0.82
     2010
    0.82
     2007
    0.79
    Act Density 0.042%

    No Known Activations