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

    Neuronpedia

    INDEX
    Explanations

    words related to years, dates, and time periods

    oai_token-act-pair · gpt-3.5-turbo

    significant years and related data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHAT
    -0.60
    plain
    -0.56
    ¬¼
    -0.55
    acting
    -0.55
     interfering
    -0.55
    Alternatively
    -0.54
     guarding
    -0.54
    oyal
    -0.54
    anooga
    -0.54
     sympath
    -0.54
    POSITIVE LOGITS
     Year
    0.86
    Year
    0.83
     2019
    0.82
     2018
    0.78
     2013
    0.75
     2011
    0.74
     calendar
    0.74
     2014
    0.74
     YEAR
    0.73
     2015
    0.73
    Act Density 0.401%

    No Known Activations