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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific name or title

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific repeated pattern or reference related to "Bre."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iating
    -0.75
    lessly
    -0.74
    orage
    -0.69
     terr
    -0.69
    ONES
    -0.68
    iated
    -0.68
    iants
    -0.67
    AGES
    -0.66
    ORED
    -0.66
     crumbling
    -0.65
    POSITIVE LOGITS
    itbart
    1.28
    thren
    1.24
    akers
    1.23
    aker
    1.21
    vity
    1.12
    aks
    1.12
    eding
    1.10
    acher
    1.06
    cht
    1.06
    tt
    1.04
    Act Density 0.022%

    No Known Activations