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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "About" or variations, indicating sections that provide information or summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ert
    -0.19
    ito
    -0.19
    orf
    -0.17
    ibil
    -0.16
    orph
    -0.16
    usc
    -0.16
    ude
    -0.15
    ose
    -0.15
    arte
    -0.15
    ault
    -0.14
    POSITIVE LOGITS
    Äįer
    0.15
    ÑĤÑİ
    0.15
    mittel
    0.14
    phia
    0.14
     Ember
    0.14
    ãİ
    0.14
    azio
    0.14
    ëĭĪ
    0.13
    iaux
    0.13
    andom
    0.13
    Act Density 0.004%

    No Known Activations