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

    Neuronpedia

    INDEX
    Explanations

    specific symbols or markers

    oai_token-act-pair · gpt-3.5-turbo

    symbols that represent special characters or formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conn
    -0.83
    oké
    -0.79
    zbek
    -0.74
    repre
    -0.73
    abl
    -0.73
    opian
    -0.70
    osh
    -0.70
    orters
    -0.69
    jack
    -0.68
    ibly
    -0.68
    POSITIVE LOGITS
     Various
    1.07
     Provides
    1.07
     Completed
    1.06
     Featuring
    1.03
     Introduction
    1.02
     [|
    1.02
     Announce
    1.02
     Contains
    0.99
     Died
    0.99
     Miscellaneous
    0.98
    Act Density 0.090%

    No Known Activations