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

    Neuronpedia

    INDEX
    Explanations

    political terms and survey-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    demographic data regarding political affiliations and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     graft
    -0.80
     salvage
    -0.78
     cloning
    -0.75
     manufact
    -0.74
     cabal
    -0.74
     rehab
    -0.73
     malf
    -0.70
    ulence
    -0.70
     scramble
    -0.70
     malfunction
    -0.70
    POSITIVE LOGITS
     polled
    1.09
     surveyed
    1.09
     respondents
    1.01
    agree
    0.99
     Gallup
    0.95
     undecided
    0.87
    avorable
    0.84
     respondent
    0.83
    aukee
    0.83
     Pew
    0.80
    Act Density 0.505%

    No Known Activations