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

    Neuronpedia

    INDEX
    Explanations

    references to famous individuals with epithets like "the sage," "the true," "the most renowned," and their accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Urug
    -0.74
     Guatem
    -0.70
     Ney
    -0.67
    obos
    -0.64
     Kro
    -0.63
     Monstrous
    -0.62
     Moreno
    -0.61
    Iv
    -0.60
     Blanc
    -0.60
     Uruguay
    -0.60
    POSITIVE LOGITS
    asonable
    0.66
     ancest
    0.65
    hire
    0.65
    vernment
    0.64
    ãĥł
    0.62
    ··
    0.60
    arf
    0.60
    flat
    0.59
    anse
    0.58
    hemy
    0.58
    Act Density 0.326%

    No Known Activations