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

    Neuronpedia

    INDEX
    Explanations

    terms related to politics and public service

    oai_token-act-pair · gpt-3.5-turbo

    references to constituents or groups of people represented by political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imb
    -0.81
    ammers
    -0.76
    oon
    -0.75
    obar
    -0.68
    ahime
    -0.67
    phal
    -0.66
    kefeller
    -0.65
    Chain
    -0.64
    central
    -0.64
    ibal
    -0.63
    POSITIVE LOGITS
     constituents
    1.05
     constituent
    0.91
     ancest
    0.81
    arians
    0.79
    hetical
    0.70
    è»
    0.70
    atives
    0.70
    reetings
    0.69
     constituencies
    0.69
    iations
    0.68
    Act Density 0.011%

    No Known Activations