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

    Neuronpedia

    INDEX
    Explanations

    the word "Bel" followed by another word, potentially related to locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Bel," indicating a focus on a specific term or concept associated with a location or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Regulation
    -0.81
    videos
    -0.75
    enegger
    -0.68
    anwhile
    -0.67
    ebook
    -0.66
     "$:/
    -0.66
    dfx
    -0.64
    ORGE
    -0.62
     Thumbnails
    -0.62
    ãģ¦
    -0.62
    POSITIVE LOGITS
    iever
    1.26
    ieving
    1.22
    ievers
    1.17
    phe
    1.03
    oit
    1.00
    ieve
    0.99
    inda
    0.99
    ieves
    0.98
    ieved
    0.96
    ongs
    0.96
    Act Density 0.010%

    No Known Activations