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

    Neuronpedia

    INDEX
    Explanations

    mentions of intelligence operations or agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to intelligence agencies or related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coni
    -0.79
    à
    -0.71
    nered
    -0.71
    zl
    -0.70
    oran
    -0.66
    alone
    -0.66
    jc
    -0.66
    oric
    -0.65
     Claus
    -0.64
    atern
    -0.63
    POSITIVE LOGITS
    elligence
    1.06
     intelligence
    1.05
     Intelligence
    0.88
     briefings
    0.86
     analytics
    0.86
     interception
    0.85
     enhancement
    0.83
     behavi
    0.81
     appraisal
    0.81
     analyst
    0.80
    Act Density 0.011%

    No Known Activations