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

    Neuronpedia

    INDEX
    Explanations

    dates represented in a specific format (day/month/year)

    oai_token-act-pair · gpt-3.5-turbo

    numeric data related to updates or versions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sooner
    -0.74
     divest
    -0.69
     brim
    -0.68
     Rand
    -0.68
     Arabian
    -0.63
     boast
    -0.61
     guilt
    -0.61
     immortality
    -0.61
     shoulder
    -0.60
     lines
    -0.60
    POSITIVE LOGITS
    2018
    1.84
    2017
    1.77
    2016
    1.76
    2014
    1.74
    2012
    1.71
    2013
    1.71
    2015
    1.70
    2006
    1.65
    2004
    1.62
    2011
    1.62
    Act Density 0.035%

    No Known Activations