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

    Neuronpedia

    INDEX
    Explanations

    references to political positions and leadership roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.63
    CppMethod
    -0.62
    Mitarbeiter
    -0.59
    Analyst
    -0.55
     staffers
    -0.55
    STAFF
    -0.54
     STAFF
    -0.53
    スタッフ
    -0.52
    Diweddarwch
    -0.52
    ipedi
    -0.51
    POSITIVE LOGITS
     president
    0.86
     President
    0.79
     leader
    0.61
    president
    0.59
     governor
    0.57
    President
    0.57
     presidente
    0.55
     PRESIDENT
    0.55
     emperor
    0.52
     Governor
    0.52
    Act Density 0.476%

    No Known Activations