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

    Neuronpedia

    INDEX
    Explanations

    references to a "pool."

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of pools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rians
    -0.74
    NESS
    -0.72
    rian
    -0.71
    eme
    -0.70
    DonaldTrump
    -0.64
     Realms
    -0.64
    orial
    -0.64
    sbm
    -0.60
    ®
    -0.59
     Cel
    -0.59
    POSITIVE LOGITS
     pool
    1.11
    pool
    1.05
    esville
    1.03
     Pool
    0.96
     pools
    0.96
    eries
    0.89
    regate
    0.87
    side
    0.84
    hare
    0.80
    erves
    0.77
    Act Density 0.028%

    No Known Activations