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

    Neuronpedia

    INDEX
    Explanations

    elements related to espionage and undercover activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resenter
    -0.15
    CLU
    -0.15
    åĩĿ
    -0.14
    idot
    -0.14
     gst
    -0.14
    erli
    -0.14
    ernaut
    -0.14
    aye
    -0.13
    .creator
    -0.13
     assault
    -0.13
    POSITIVE LOGITS
     agent
    0.33
     agents
    0.30
     Agents
    0.29
    agent
    0.28
     Agent
    0.28
     operatives
    0.27
     intelligence
    0.27
     CIA
    0.26
    -agent
    0.26
     Intelligence
    0.25
    Act Density 0.098%

    No Known Activations