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

    Neuronpedia

    INDEX
    Explanations

    names the name "James" occurring in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "James" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sites
    -0.78
    cert
    -0.69
    cers
    -0.68
    cision
    -0.68
    Ĥª
    -0.65
    yards
    -0.65
    nown
    -0.64
    iously
    -0.62
    struct
    -0.62
    aneous
    -0.62
    POSITIVE LOGITS
     Beard
    0.98
     Harden
    0.98
     Madison
    0.94
     Clapper
    0.92
     Franco
    0.92
     Gunn
    0.89
     Joyce
    0.88
     Clerk
    0.87
     Comey
    0.86
     Bond
    0.85
    Act Density 0.018%

    No Known Activations