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

    Neuronpedia

    INDEX
    Explanations

    references to espionage and intelligence agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ§
    -0.15
    ecast
    -0.15
    hetto
    -0.15
    .createFrom
    -0.15
     vandal
    -0.14
    anned
    -0.14
    Collision
    -0.14
     Pir
    -0.14
    OUCH
    -0.13
     Municipal
    -0.13
    POSITIVE LOGITS
     agents
    0.34
     Agent
    0.33
     agent
    0.33
     Agents
    0.32
    -agent
    0.30
    agent
    0.29
    Agent
    0.29
     CIA
    0.28
     Agency
    0.28
    -Agent
    0.28
    Act Density 0.329%

    No Known Activations