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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures and news events

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to political figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     metre
    -0.72
     realised
    -0.71
    ĸļ
    -0.70
     Jagu
    -0.68
     realise
    -0.66
     analyse
    -0.66
     metab
    -0.65
     explorers
    -0.65
    gements
    -0.64
     organise
    -0.64
    POSITIVE LOGITS
     Republican
    1.12
     Politico
    1.07
     GOP
    1.06
    Republicans
    1.05
    Republican
    1.04
    partisan
    1.04
     bipartisan
    1.04
     Hillary
    1.00
    Hillary
    1.00
     Republicans
    0.98
    Act Density 2.362%

    No Known Activations