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

    Neuronpedia

    INDEX
    Explanations

    mentions of deadlines or time frames for certain actions or events

    oai_token-act-pair · gpt-3.5-turbo

    predictions or commitments regarding future policy changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esta
    -0.82
    Reviewer
    -0.75
    IENT
    -0.73
     surprises
    -0.66
    >[
    -0.66
    ractor
    -0.62
     breakout
    -0.61
    elo
    -0.59
    ibli
    -0.58
    APD
    -0.57
    POSITIVE LOGITS
     2020
    0.98
     lest
    0.98
     indefinitely
    0.93
     2021
    0.91
     2025
    0.91
     outlawed
    0.85
    instead
    0.84
     2022
    0.81
     Instead
    0.80
     2024
    0.80
    Act Density 0.805%

    No Known Activations