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

    Neuronpedia

    INDEX
    Explanations

    political terms related to media and influence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to deception and manipulation by the media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    offer
    -0.71
     disputed
    -0.71
    vari
    -0.70
    rawling
    -0.67
    tnc
    -0.67
    elcome
    -0.66
     distinctive
    -0.65
    risk
    -0.65
     tense
    -0.64
    uberty
    -0.64
    POSITIVE LOGITS
     pundits
    1.46
     bureaucrats
    1.27
     neocons
    1.15
     elites
    1.15
     pund
    1.15
     cabal
    1.13
     idiots
    1.12
     commentators
    1.12
     liberals
    1.10
     lobbyists
    1.08
    Act Density 0.647%

    No Known Activations