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

    Neuronpedia

    INDEX
    Explanations

    references to political staffers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of staffers or personnel in a professional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lass
    -0.76
    lasses
    -0.74
     ..
    -0.72
    emonic
    -0.69
    ende
    -0.67
     uncond
    -0.67
     society
    -0.65
     Bos
    -0.64
    othe
    -0.64
     mat
    -0.62
    POSITIVE LOGITS
     staffers
    2.71
     staffer
    2.71
     interns
    1.19
     lobbyist
    0.93
     insiders
    0.91
     lobbyists
    0.90
     Reps
    0.89
    Care
    0.88
     exec
    0.85
     alum
    0.85
    Act Density 0.023%

    No Known Activations