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

    Neuronpedia

    INDEX
    Explanations

    information related to politics and government, particularly pertaining to ruling parties

    oai_token-act-pair · gpt-3.5-turbo

    references to ruling political parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lished
    -0.86
    gomery
    -0.79
    gm
    -0.69
    orrow
    -0.66
    emis
    -0.66
    ifix
    -0.66
    vey
    -0.66
    okane
    -0.65
    chie
    -0.64
    ufact
    -0.64
    POSITIVE LOGITS
     coalition
    0.95
     party
    0.90
     elite
    0.86
     elites
    0.83
     bloc
    0.82
     class
    0.81
     Workers
    0.79
     Conservatives
    0.79
     apparatus
    0.78
     Communist
    0.76
    Act Density 0.042%

    No Known Activations