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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    references to burial sites or tombs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rament
    -0.71
    tag
    -0.70
    DI
    -0.64
    SpaceEngineers
    -0.63
     ageing
    -0.63
     beneficiary
    -0.63
    stri
    -0.61
     Converted
    -0.61
    stretched
    -0.60
     Shed
    -0.60
    POSITIVE LOGITS
    ombs
    3.63
    zens
    2.06
    aber
    1.24
    ppel
    1.12
    omas
    1.09
     timed
    1.06
    nels
    1.04
    nant
    0.99
    poons
    0.99
    omsday
    0.93
    Act Density 0.050%

    No Known Activations