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

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    specific month names from a timeline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cedes
    -0.71
    etooth
    -0.69
    izabeth
    -0.67
    egal
    -0.66
    speak
    -0.63
    isine
    -0.62
    desc
    -0.61
    amines
    -0.60
    pract
    -0.60
     sacrific
    -0.59
    POSITIVE LOGITS
     2016
    0.97
     2015
    0.97
     2017
    0.93
     2014
    0.91
     2013
    0.90
     2011
    0.88
     2012
    0.88
     2010
    0.86
     2009
    0.85
    flower
    0.84
    Act Density 0.059%

    No Known Activations