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

    Neuronpedia

    INDEX
    Explanations

    keywords related to architectural elements or structures

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awar
    -0.77
    vous
    -0.72
    bring
    -0.72
    aneous
    -0.68
     Mississ
    -0.68
    tein
    -0.68
    ting
    -0.67
    emade
    -0.67
     Hubbard
    -0.67
    eworthy
    -0.66
    POSITIVE LOGITS
    itect
    1.21
    urally
    1.11
     architecture
    1.06
    ural
    0.94
     architect
    0.88
     Architecture
    0.83
     architectures
    0.81
     mismatch
    0.81
     diagram
    0.77
     flaw
    0.76
    Act Density 0.015%

    No Known Activations