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

    Neuronpedia

    INDEX
    Explanations

    references to contacting or reaching out to someone or an organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of site communication pages or sections, especially when appearing as headers or in code identifiers.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab

    Contact

    np_max-act-logits · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
    guiente
    -0.62
     Keuangan
    -0.54
     esimer
    -0.54
     mesmas
    -0.52
     '\\;'
    -0.52
    guenos
    -0.51
     дописавши
    -0.49
    writerow
    -0.48
     rootReducer
    -0.48
    pecabe
    -0.47
    POSITIVE LOGITS
    contact
    1.21
     contact
    1.18
    Contact
    1.11
     Contact
    1.09
    CONTACT
    1.02
     CONTACT
    1.02
     contacts
    0.94
    contacts
    0.91
     Contacts
    0.88
    Contacts
    0.86
    Act Density 0.109%

    No Known Activations