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

    Neuronpedia

    INDEX
    Explanations

    references to specific years or numeric data in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mechanic
    -0.15
    emin
    -0.14
    angu
    -0.14
    ovid
    -0.14
    etect
    -0.13
    彦
    -0.13
    .orange
    -0.13
    ALLED
    -0.13
    ottle
    -0.13
    ays
    -0.13
    POSITIVE LOGITS
    isas
    0.16
    kea
    0.16
    ÑĮе
    0.15
    _cached
    0.14
     promises
    0.14
    aign
    0.14
    enu
    0.14
    ancellationToken
    0.14
    ëĵĿ
    0.14
    å¹´
    0.13
    Act Density 0.058%

    No Known Activations