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

    Neuronpedia

    INDEX
    Explanations

    references to specific laws or legal acts

    oai_token-act-pair · gpt-3.5-turbo

    references to legal acts and laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.80
    auga
    -0.80
    ertodd
    -0.67
    ername
    -0.67
    uyomi
    -0.66
    ovie
    -0.64
     Inquis
    -0.62
    bryce
    -0.61
    ppa
    -0.61
    ritz
    -0.61
    POSITIVE LOGITS
     conscience
    0.71
    writ
    0.68
    urance
    0.65
    icial
    0.64
     course
    0.62
    written
    0.62
     mind
    0.60
    Record
    0.59
    ogenesis
    0.58
    wrote
    0.58
    Act Density 0.193%

    No Known Activations