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

    Neuronpedia

    INDEX
    Explanations

    references to domains or domain concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clegg
    -0.73
     McClure
    -0.68
     devons
    -0.66
     engagé
    -0.62
    หมือน
    -0.62
     scio
    -0.61
    appoint
    -0.60
     καλ
    -0.60
    ~•
    -0.60
     Nunn
    -0.60
    POSITIVE LOGITS
     domain
    2.70
     Domain
    2.57
     domains
    2.47
    domain
    2.40
    Domain
    2.37
     Domains
    2.24
     DOMAIN
    2.22
    DOMAIN
    2.14
    domains
    2.06
    Domains
    2.04
    Act Density 0.044%

    No Known Activations