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

    Neuronpedia

    INDEX
    Explanations

    references to a specific political news outlet

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the news outlet Politico

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lights
    -0.79
    ysis
    -0.77
    isted
    -0.76
     WWF
    -0.76
    oji
    -0.68
    cknowled
    -0.64
    ighters
    -0.64
    igned
    -0.64
    ettel
    -0.64
    umar
    -0.64
    POSITIVE LOGITS
     Caucus
    0.93
     Magazine
    0.90
     Digest
    0.78
     aide
    0.76
     Heights
    0.75
     Insider
    0.75
     Tanz
    0.73
     Kills
    0.73
    icago
    0.71
    clinton
    0.71
    Act Density 0.006%

    No Known Activations