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

    Neuronpedia

    INDEX
    Explanations

    mentions of the CIA and related job titles

    oai_token-act-pair · gpt-3.5-turbo

    references to the CIA and its directors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mulcair
    -0.79
    ghai
    -0.76
    hips
    -0.74
    steen
    -0.72
    abeth
    -0.71
    kees
    -0.70
    nings
    -0.70
     Bieber
    -0.69
    igans
    -0.69
    borgh
    -0.68
    POSITIVE LOGITS
     Director
    1.02
     annex
    1.01
     operatives
    0.93
     operative
    0.92
     Headquarters
    0.90
     headquarters
    0.86
     director
    0.85
    andestine
    0.84
     whistleblower
    0.83
     agents
    0.83
    Act Density 0.026%

    No Known Activations