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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intelligence agencies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intelligence and intelligence agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nered
    -0.80
    ikan
    -0.73
    ifest
    -0.71
    itol
    -0.70
    zl
    -0.70
    oran
    -0.70
    olds
    -0.70
     Roof
    -0.67
    )=(
    -0.67
    ivas
    -0.67
    POSITIVE LOGITS
     briefings
    1.05
     analyst
    0.93
     agencies
    0.89
     agency
    0.87
     bulletin
    0.87
     Agency
    0.83
     quot
    0.83
     analysts
    0.83
    agency
    0.82
     officer
    0.81
    Act Density 0.023%

    No Known Activations