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

    Neuronpedia

    INDEX
    Explanations

    governmental or formal requests or calls to action

    oai_token-act-pair · gpt-3.5-turbo

    references to government and political entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spo
    -0.64
    )?
    -0.62
     crosses
    -0.61
    zsche
    -0.60
     quot
    -0.58
     intrigue
    -0.58
    acular
    -0.57
     ling
    -0.56
    estyles
    -0.56
    edition
    -0.56
    POSITIVE LOGITS
    DERR
    0.76
     authorities
    0.74
     regulators
    0.71
    NEY
    0.70
    istries
    0.70
    Secretary
    0.68
     Investors
    0.68
     brass
    0.67
     policymakers
    0.65
    SEE
    0.65
    Act Density 0.422%

    No Known Activations