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

    Neuronpedia

    INDEX
    Explanations

    references to architectural structures or features

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awar
    -0.76
    bring
    -0.74
     Kers
    -0.70
     Hubbard
    -0.69
    vous
    -0.68
    rd
    -0.67
    Scot
    -0.67
    ml
    -0.66
     Quit
    -0.66
    chenko
    -0.65
    POSITIVE LOGITS
    itect
    1.16
    urally
    1.08
     architecture
    1.08
    ural
    0.94
     Architecture
    0.91
     architectures
    0.84
     architect
    0.81
     mismatch
    0.79
     skysc
    0.78
     architectural
    0.76
    Act Density 0.015%

    No Known Activations