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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific location or figure - "Bel"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term 'Bel', likely referring to a specific name or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Regulation
    -0.81
    videos
    -0.79
    DragonMagazine
    -0.77
    enegger
    -0.76
    anwhile
    -0.73
    displayText
    -0.68
    ebook
    -0.68
     "$:/
    -0.67
    ORGE
    -0.66
    ograp
    -0.66
    POSITIVE LOGITS
    iever
    1.26
    ieving
    1.22
    ievers
    1.16
    inda
    0.97
    oit
    0.96
    phe
    0.96
    ieves
    0.96
    ieved
    0.94
    ieve
    0.92
    ongs
    0.90
    Act Density 0.007%

    No Known Activations