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

    Neuronpedia

    INDEX
    Explanations

    politicians and their respective states and parties

    oai_token-act-pair · gpt-3.5-turbo

    negative political sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.87
    llah
    -0.85
    obyl
    -0.83
    urden
    -0.66
    tics
    -0.62
     radar
    -0.61
    htaking
    -0.61
     cache
    -0.61
     icing
    -0.61
     layer
    -0.60
    POSITIVE LOGITS
    adj
    1.02
    nom
    0.98
    California
    0.95
    Calif
    0.91
    member
    0.87
    affiliated
    0.86
    ranked
    0.84
    prime
    0.81
    GG
    0.81
    degree
    0.80
    Act Density 0.044%

    No Known Activations