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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures holding office

    oai_token-act-pair · gpt-3.5-turbo

    references to incumbents in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.95
    ooter
    -0.85
    kie
    -0.85
    okin
    -0.83
    atche
    -0.81
    apa
    -0.80
    ombs
    -0.80
    oho
    -0.79
    tera
    -0.78
    hran
    -0.78
    POSITIVE LOGITS
     incumbent
    1.03
     challenger
    0.90
     frontrunner
    0.84
     challengers
    0.83
     incumb
    0.82
     tenant
    0.80
     opponent
    0.80
     loser
    0.80
     foe
    0.77
     occupant
    0.77
    Act Density 0.025%

    No Known Activations