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

    Neuronpedia

    INDEX
    Explanations

    mentions of political oversight and surveillance activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egas
    -0.16
    loff
    -0.16
    adan
    -0.14
    enÄĽ
    -0.14
     ara
    -0.14
    Gas
    -0.14
     Gas
    -0.14
    ofire
    -0.14
    oser
    -0.14
    okt
    -0.13
    POSITIVE LOGITS
     surveillance
    0.30
     NSA
    0.30
     Bulk
    0.29
     bulk
    0.29
     Surveillance
    0.27
     Prism
    0.26
     metadata
    0.26
    bulk
    0.26
     surve
    0.25
    Bulk
    0.25
    Act Density 0.044%

    No Known Activations