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

    Neuronpedia

    INDEX
    Explanations

    keywords related to organized groups or communities

    oai_token-act-pair · gpt-3.5-turbo

    references to various organizations or collectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rah
    -0.75
    wards
    -0.65
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.63
     Mansion
    -0.62
     Guards
    -0.62
     Hou
    -0.61
    âĺħâĺħ
    -0.61
    OUS
    -0.60
    shire
    -0.59
     Kardashian
    -0.59
    POSITIVE LOGITS
    etter
    0.91
    roups
    0.89
    hell
    0.88
    wana
    0.87
    erv
    0.85
    folk
    0.84
    arettes
    0.82
     nonprofits
    0.82
    achu
    0.82
    anguage
    0.81
    Act Density 0.034%

    No Known Activations