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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names and terms related to politics, especially the term "populist"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of politicians and references to populism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -0.99
    ly
    -0.95
    bies
    -0.88
    ez
    -0.85
    rence
    -0.83
    hent
    -0.83
    dar
    -0.82
    rine
    -0.82
    rament
    -0.81
    rences
    -0.78
    POSITIVE LOGITS
    OWER
    0.74
    ieri
    0.68
    ocr
    0.64
    ength
    0.63
    igers
    0.63
     cords
    0.62
    ucci
    0.61
    anced
    0.60
    enged
    0.59
    uzzle
    0.58
    Act Density 0.106%

    No Known Activations