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

    Neuronpedia

    INDEX
    Explanations

    dates in the format Month.Day Year and related calendar events

    oai_token-act-pair · gpt-3.5-turbo

    dates and associated numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     er
    -0.64
    orically
    -0.64
     ware
    -0.62
    orical
    -0.61
    arios
    -0.60
     Wasserman
    -0.60
     quot
    -0.58
    abad
    -0.57
     collateral
    -0.57
     grease
    -0.57
    POSITIVE LOGITS
     2019
    0.89
    pole
    0.78
     2018
    0.75
    γ
    0.75
     2017
    0.74
    HCR
    0.72
    vier
    0.71
    2018
    0.70
     2025
    0.68
    1997
    0.68
    Act Density 0.127%

    No Known Activations