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

    Neuronpedia

    INDEX
    Explanations

    references to architectural terms or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zers
    -0.19
    ovich
    -0.17
    ucci
    -0.16
     cub
    -0.15
    arium
    -0.15
    orf
    -0.15
    itor
    -0.15
    arpa
    -0.14
    omorphic
    -0.14
    quot
    -0.14
    POSITIVE LOGITS
    ipel
    0.33
    itect
    0.28
    bishop
    0.24
    itecture
    0.24
    angel
    0.23
    etype
    0.23
    etypes
    0.23
    uate
    0.20
     arch
    0.19
    ivist
    0.19
    Act Density 0.013%

    No Known Activations