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

    Neuronpedia

    INDEX
    Explanations

    collections or groups of related items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to collections and quantities of works or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    slow
    -0.74
     bye
    -0.65
     Commissioners
    -0.62
    verbs
    -0.61
    death
    -0.61
     Lady
    -0.58
     harmless
    -0.58
     Commissioner
    -0.58
     slightest
    -0.57
     Declaration
    -0.57
    POSITIVE LOGITS
    ipel
    0.89
     spanning
    0.88
    ortment
    0.87
    DragonMagazine
    0.87
    ĸļ
    0.85
     spans
    0.81
    icity
    0.76
    naire
    0.75
     encomp
    0.74
     catalogue
    0.73
    Act Density 0.150%

    No Known Activations