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

    Neuronpedia

    INDEX
    Explanations

    references to a specific location or entity spelled as 'pool'

    oai_token-act-pair · gpt-3.5-turbo

    references to pools or groupings related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rians
    -0.83
    rian
    -0.74
     Cel
    -0.68
    DonaldTrump
    -0.68
    eme
    -0.67
    NESS
    -0.66
     Realms
    -0.61
     WTO
    -0.60
     Loving
    -0.60
    ======
    -0.59
    POSITIVE LOGITS
     pool
    1.13
    esville
    1.10
    pool
    1.06
     Pool
    1.00
     pools
    0.95
    regate
    0.90
    eries
    0.88
    side
    0.87
    erves
    0.83
    hare
    0.79
    Act Density 0.023%

    No Known Activations