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

    Neuronpedia

    INDEX
    Explanations

    words related to architecture

    oai_token-act-pair · gpt-3.5-turbo

    references to architectural concepts and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mew
    -0.68
    Pos
    -0.67
    erves
    -0.66
    stick
    -0.66
    ighters
    -0.64
    LT
    -0.64
     Rebell
    -0.64
    nings
    -0.63
    checked
    -0.63
    CTV
    -0.63
    POSITIVE LOGITS
     architecture
    3.76
     Architecture
    3.03
     architectures
    2.47
     architectural
    2.43
     Architect
    2.00
     architects
    1.88
    itect
    1.85
     architect
    1.83
     Architects
    1.52
     geometry
    1.37
    Act Density 0.014%

    No Known Activations