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

    Neuronpedia

    INDEX
    Explanations

    references to governmental institutions, particularly the White House

    oai_token-act-pair · gpt-3.5-turbo

    references to government entities and official organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernels
    -0.96
    tags
    -0.89
    rencies
    -0.87
    bats
    -0.85
    stones
    -0.83
    eworks
    -0.80
    classes
    -0.80
     Machines
    -0.79
    Tags
    -0.78
    events
    -0.77
    POSITIVE LOGITS
     staffer
    1.14
     colleague
    1.13
     spokeswoman
    1.11
     spokesman
    1.07
     spokesperson
    1.05
     aide
    0.98
     official
    0.97
     representative
    0.95
     employee
    0.89
     ally
    0.89
    Act Density 0.323%

    No Known Activations