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

    Neuronpedia

    INDEX
    Explanations

    terms related to architecture and architectural design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     architectures
    -0.20
     Architects
    -0.18
     architecture
    -0.18
    erator
    -0.18
     Architecture
    -0.18
    arious
    -0.17
    tings
    -0.16
    architecture
    -0.16
    Architecture
    -0.15
    _arch
    -0.15
    POSITIVE LOGITS
    ural
    0.40
    urally
    0.40
    /engine
    0.28
    URAL
    0.27
     firm
    0.24
    å¸Ī
    0.24
     sÆ°
    0.24
     firms
    0.23
    師
    0.22
    ur
    0.22
    Act Density 0.018%

    No Known Activations