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

    Neuronpedia

    INDEX
    Explanations

    references to leadership and authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    leader and leadership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $
    -0.35
     vuông
    -0.35
    Activités
    -0.30
     window
    -0.30
     fancy
    -0.30
     spesial
    -0.30
     Japanese
    -0.30
     curiosity
    -0.29
    packung
    -0.29
     мона
    -0.29
    POSITIVE LOGITS
     leader
    0.82
    leader
    0.75
     leaders
    0.73
    leaders
    0.73
    Leaders
    0.73
     pemimpin
    0.69
    таратура
    0.69
    LookAnd
    0.64
     líderes
    0.64
    parsedMessage
    0.64
    Act Density 0.012%

    No Known Activations