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

    Neuronpedia

    INDEX
    Explanations

    dates expressed in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glim
    -0.91
    ometimes
    -0.71
     fingert
    -0.70
    uffer
    -0.63
    pend
    -0.61
    natureconservancy
    -0.61
    ourge
    -0.59
     marqu
    -0.59
     nodd
    -0.58
     weap
    -0.58
    POSITIVE LOGITS
     2015
    1.13
     2016
    1.11
     2013
    1.09
     2017
    1.09
     2018
    1.07
     2014
    1.07
     2010
    1.05
     2009
    1.01
     2011
    1.01
     2012
    0.99
    Act Density 0.044%

    No Known Activations