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

    Neuronpedia

    INDEX
    Explanations

    mentions of prior experience or lack thereof in different contexts such as legal, military, and programming

    oai_token-act-pair · gpt-3.5-turbo

    references to professional experience and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipples
    -0.75
    ollow
    -0.74
    Slow
    -0.74
    wake
    -0.73
     Slowly
    -0.72
    irds
    -0.71
    Pand
    -0.71
    fires
    -0.69
    iatus
    -0.69
    sylv
    -0.68
    POSITIVE LOGITS
     qualifications
    1.53
     expertise
    1.45
     skills
    1.41
     credentials
    1.40
     pedigree
    1.36
     competence
    1.29
     backgrounds
    1.26
     knowledge
    1.26
     ré
    1.24
     charisma
    1.24
    Act Density 0.579%

    No Known Activations