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

    Neuronpedia

    INDEX
    Explanations

    dates written in month, day, and year format

    oai_token-act-pair · gpt-3.5-turbo

    dates mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opic
    -0.78
     predec
    -0.74
     glim
    -0.70
     liner
    -0.68
     cumbers
    -0.66
    Continue
    -0.63
     grou
    -0.62
     patriarch
    -0.62
     bom
    -0.62
     princ
    -0.61
    POSITIVE LOGITS
     âĶľ
    0.94
     2018
    0.92
     2015
    0.88
     2016
    0.88
     2017
    0.87
     onwards
    0.85
     2014
    0.85
     2013
    0.82
     2012
    0.79
     2019
    0.77
    Act Density 0.033%

    No Known Activations