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

    Neuronpedia

    INDEX
    Explanations

    words related to issues, problems, and deficiencies

    oai_token-act-pair · gpt-3.5-turbo

    issues related to problems and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endorsements
    -0.70
     nods
    -0.68
     Pledge
    -0.67
     dances
    -0.67
     ceremonies
    -0.67
     Values
    -0.65
     CHO
    -0.65
     offerings
    -0.64
     commissions
    -0.63
     oath
    -0.63
    POSITIVE LOGITS
     exacerbated
    1.20
     remed
    1.18
     worsened
    1.12
     severity
    1.12
     caused
    1.09
     resolved
    1.08
     solved
    1.07
     manageable
    1.04
     worse
    1.03
     cured
    1.02
    Act Density 0.708%

    No Known Activations