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

    Neuronpedia

    INDEX
    Explanations

    words related to intelligence agencies and committees

    oai_token-act-pair · gpt-3.5-turbo

    references to intelligence agencies and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zl
    -0.75
    interstitial
    -0.72
    emp
    -0.71
    anan
    -0.70
    haw
    -0.70
    loading
    -0.68
    yards
    -0.68
    unin
    -0.67
    artifacts
    -0.66
     unreal
    -0.65
    POSITIVE LOGITS
     Agency
    1.00
     Bureau
    0.91
     Surveillance
    0.87
     Committee
    0.80
     Intelligence
    0.80
    elligence
    0.79
    atform
    0.78
     Authorization
    0.76
     Oversight
    0.75
    iator
    0.75
    Act Density 0.024%

    No Known Activations