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

    Neuronpedia

    INDEX
    Explanations

    references to domains and their various attributes within different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Schutz
    -0.66
     instru
    -0.66
     καλ
    -0.66
    icleta
    -0.66
     tryp
    -0.65
     obligé
    -0.65
     devons
    -0.64
     farb
    -0.61
    款
    -0.59
     engagé
    -0.59
    POSITIVE LOGITS
     Domain
    1.77
     domain
    1.75
     domains
    1.75
     Domains
    1.67
     DOMAIN
    1.59
    DOMAIN
    1.52
    domains
    1.51
    Domain
    1.50
    domain
    1.46
    Domains
    1.41
    Act Density 0.106%

    No Known Activations