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

    Neuronpedia

    INDEX
    Explanations

    references to specific amounts of monetary values

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to large financial amounts or economic metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dull
    -0.73
     Niet
    -0.69
     flair
    -0.64
    mons
    -0.62
     Hubbard
    -0.62
    othy
    -0.62
    ij士
    -0.61
     Ferr
    -0.61
     demeanor
    -0.60
     Vander
    -0.60
    POSITIVE LOGITS
     (£
    1.16
    illion
    1.06
    £
    1.00
    ilion
    0.90
    omination
    0.88
    itte
    0.87
    ulent
    0.80
    imet
    0.80
    ocular
    0.80
    sov
    0.80
    Act Density 0.013%

    No Known Activations