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

    Neuronpedia

    INDEX
    Explanations

    references to future years, particularly the year 2030

    oai_token-act-pair · gpt-3.5-turbo

    references to specific future years, particularly 2030 and 2050

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tub
    -0.76
    sem
    -0.75
    isy
    -0.75
    ESSION
    -0.69
    hemat
    -0.68
    unal
    -0.67
    oyal
    -0.67
    uan
    -0.66
    Attorney
    -0.66
    aws
    -0.65
    POSITIVE LOGITS
     2025
    1.25
     2030
    1.19
     2050
    1.10
    ãĤ¼ãĤ¦ãĤ¹
    1.10
     2020
    1.03
    2020
    0.97
     2021
    0.91
     2022
    0.85
     2024
    0.81
     2019
    0.81
    Act Density 0.006%

    No Known Activations