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

    Neuronpedia

    INDEX
    Explanations

    dates in the format "Month Day" (e.g. "February 9")

    oai_token-act-pair · gpt-3.5-turbo

    dates, particularly in the month of February

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cumbers
    -0.74
    eteria
    -0.73
    alach
    -0.67
    ographed
    -0.67
     behavi
    -0.66
    ullivan
    -0.63
    ioch
    -0.63
     VIDEOS
    -0.62
    ecast
    -0.61
    afer
    -0.60
    POSITIVE LOGITS
    nd
    1.04
     2019
    1.04
     2017
    0.96
     2015
    0.92
     2021
    0.92
     2016
    0.89
     Madness
    0.89
     2018
    0.89
     2024
    0.88
    riage
    0.84
    Act Density 0.012%

    No Known Activations