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

    Neuronpedia

    INDEX
    Explanations

    statements regarding future plans or projections

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate time frames or deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.74
    asive
    -0.68
    SPONSORED
    -0.68
    ocal
    -0.65
    bleacher
    -0.62
    arious
    -0.61
     glances
    -0.60
    puff
    -0.60
    wic
    -0.59
    oslov
    -0.59
    POSITIVE LOGITS
     2025
    1.66
     2020
    1.64
     2021
    1.61
     2022
    1.59
     2030
    1.57
     2019
    1.55
     2024
    1.52
     2050
    1.39
     2018
    1.28
     September
    1.26
    Act Density 0.090%

    No Known Activations