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

    Neuronpedia

    INDEX
    Explanations

    mentions of government officials, political situations, and military activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ILLE
    -0.90
     Predators
    -0.88
     brim
    -0.87
     mos
    -0.87
    irc
    -0.82
    emp
    -0.82
    jad
    -0.81
    orsi
    -0.81
    river
    -0.81
    illegal
    -0.77
    POSITIVE LOGITS
    chair
    1.13
     secretary
    1.07
     Secretary
    1.06
     Rodham
    1.05
    osate
    1.00
     Clinton
    0.99
    General
    0.97
    atton
    0.97
    izont
    0.95
     secretaries
    0.95
    Act Density 0.733%

    No Known Activations