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

    Neuronpedia

    INDEX
    Explanations

    references to nonpartisan entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with neutrality and bipartisanship in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angers
    -0.82
    KT
    -0.78
    Stage
    -0.76
    Pause
    -0.74
    thur
    -0.73
    uman
    -0.70
    gars
    -0.70
    VL
    -0.70
    Pac
    -0.70
    Mist
    -0.70
    POSITIVE LOGITS
    vernment
    1.02
     nonpartisan
    0.88
     impartial
    0.86
     watchdog
    0.75
    partisan
    0.75
    artisan
    0.74
     Congressional
    0.72
    sonian
    0.72
     observer
    0.70
    irection
    0.68
    Act Density 0.015%

    No Known Activations