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

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in the context of news articles

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical values in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edom
    -0.75
     schemes
    -0.70
    anwhile
    -0.67
     exha
    -0.67
     predec
    -0.66
    userc
    -0.66
     plantations
    -0.65
     sauces
    -0.65
     expansions
    -0.64
     backups
    -0.64
    POSITIVE LOGITS
     2018
    0.86
     2017
    0.81
     2015
    0.79
     2006
    0.79
     2008
    0.78
     2002
    0.78
     2014
    0.78
     1989
    0.77
     2007
    0.77
     1988
    0.77
    Act Density 0.117%

    No Known Activations