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

    Neuronpedia

    INDEX
    Explanations

    references to covert governmental operations and intelligence activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SMP
    -0.46
     LIABLE
    -0.45
    Medi
    -0.44
    Vikt
    -0.43
     Cycle
    -0.43
    Impressum
    -0.42
    }{*}{
    -0.42
    gac
    -0.42
     Fresh
    -0.42
    WoW
    -0.42
    POSITIVE LOGITS
     espionage
    0.81
     intelligence
    0.80
     spy
    0.79
     Intelligence
    0.77
     spying
    0.74
     spies
    0.71
    Intelligence
    0.71
    intelligence
    0.69
     spion
    0.64
     CIA
    0.62
    Act Density 0.562%

    No Known Activations