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

    Neuronpedia

    INDEX
    Explanations

    references to leadership and historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avel
    -0.15
    ossa
    -0.15
    otos
    -0.15
    endra
    -0.15
    -produ
    -0.15
     Weiner
    -0.15
    aleza
    -0.14
     meisten
    -0.14
    ÃŃlia
    -0.14
     voks
    -0.14
    POSITIVE LOGITS
     presidente
    0.26
     secret
    0.25
     Secret
    0.22
     due
    0.22
     President
    0.21
     socio
    0.21
     vice
    0.21
     director
    0.20
     ger
    0.20
     mi
    0.20
    Act Density 0.032%

    No Known Activations