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

    Neuronpedia

    INDEX
    Explanations

    terms related to politics

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "political" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actory
    -0.89
    olen
    -0.88
    wered
    -0.87
     Cancel
    -0.84
    ighed
    -0.76
    IER
    -0.76
    tered
    -0.75
    imates
    -0.75
    uses
    -0.75
    imus
    -0.74
    POSITIVE LOGITS
     correctness
    1.28
     affiliation
    0.98
     affili
    0.97
     pund
    0.94
     clout
    0.94
     campaigns
    0.91
     activism
    0.87
     rhetoric
    0.87
     persuasion
    0.86
     leaders
    0.85
    Act Density 0.033%

    No Known Activations