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

    Neuronpedia

    INDEX
    Explanations

    references to spy-related themes and elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elsen
    -0.15
    ç°
    -0.14
     manslaughter
    -0.14
    arel
    -0.14
    åħ¬åijĬ
    -0.14
    ılıp
    -0.14
    _bs
    -0.13
     законодав
    -0.13
    hir
    -0.13
     discriminator
    -0.13
    POSITIVE LOGITS
     CIA
    0.41
     agent
    0.38
     spy
    0.37
     agents
    0.36
     Agents
    0.35
    -agent
    0.35
     Agent
    0.34
     spies
    0.33
     intelligence
    0.33
    agent
    0.32
    Act Density 0.230%

    No Known Activations