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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific organization or group

    oai_token-act-pair · gpt-3.5-turbo

    references to groups and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shire
    -0.71
    cale
    -0.68
    èª
    -0.64
    Rah
    -0.62
     concess
    -0.62
    LEASE
    -0.61
     Latest
    -0.60
    yy
    -0.60
     lig
    -0.60
     Shard
    -0.59
    POSITIVE LOGITS
    think
    0.96
    members
    0.95
    leader
    0.94
    arettes
    0.92
    arette
    0.91
     disbanded
    0.90
    roups
    0.87
     members
    0.87
    rooms
    0.82
    mates
    0.80
    Act Density 0.050%

    No Known Activations