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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate targets or goals for a specific year

    oai_token-act-pair · gpt-3.5-turbo

    references to timeframes and numerical projections related to environmental or demographic data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -1.06
    raq
    -0.64
     voic
    -0.63
    aline
    -0.62
     ingred
    -0.61
     baffled
    -0.58
    asive
    -0.57
     Pastebin
    -0.55
     puzzled
    -0.54
    aq
    -0.53
    POSITIVE LOGITS
     2025
    2.14
     2030
    2.09
     2024
    2.07
     2021
    2.05
     2022
    2.02
     2020
    2.00
     2050
    1.95
     2019
    1.78
    2020
    1.60
     2100
    1.55
    Act Density 0.107%

    No Known Activations