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

    Neuronpedia

    INDEX
    Explanations

    words prefixed with "re"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "re" indicating repetition or return

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.85
     Beir
    -0.77
     Pebble
    -0.77
    DragonMagazine
    -0.75
     Zamb
    -0.67
     Phar
    -0.66
     Sammy
    -0.66
     Nest
    -0.66
     Korra
    -0.64
     Kafka
    -0.63
    POSITIVE LOGITS
    venge
    1.14
    actor
    1.13
    ached
    1.11
    becca
    1.11
    porter
    1.10
    asons
    1.03
    claim
    1.02
    versible
    1.02
    venue
    1.02
    leases
    1.00
    Act Density 0.047%

    No Known Activations