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

    Neuronpedia

    INDEX
    Explanations

    references to domain-related concepts and discussions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     devons
    -0.79
     celta
    -0.72
    icleta
    -0.69
     McClure
    -0.68
    >//
    -0.68
     engagé
    -0.67
     Clegg
    -0.67
    Schutz
    -0.66
     Scud
    -0.65
     tryp
    -0.65
    POSITIVE LOGITS
     domain
    2.00
     Domain
    1.95
     domains
    1.86
    Domain
    1.74
     DOMAIN
    1.73
    domain
    1.72
     Domains
    1.71
    DOMAIN
    1.64
    domains
    1.57
    Domains
    1.52
    Act Density 0.076%

    No Known Activations