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

    Neuronpedia

    INDEX
    Explanations

    mentions of health, medical conditions, and medical treatment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to societal changes and public opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )!
    -0.71
    ³³
    -0.65
    ³³³³
    -0.59
    )...
    -0.57
    !).
    -0.56
    ³³³³³³³³³³³³³³³³
    -0.55
    )?
    -0.55
    ↵Âł
    -0.54
    ³³³
    -0.52
     Died
    -0.52
    POSITIVE LOGITS
     unfavorable
    0.60
     ObamaCare
    0.58
     taxpayer
    0.58
     outweigh
    0.56
     lawmakers
    0.56
     politically
    0.55
    polit
    0.53
    ratom
    0.52
     Obamacare
    0.52
     unpopular
    0.51
    Act Density 2.791%

    No Known Activations