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

    Neuronpedia

    INDEX
    Explanations

    terms related to architectural styles and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eworthy
    -0.77
    awar
    -0.74
    vous
    -0.72
     Boone
    -0.70
     Rober
    -0.68
    pload
    -0.68
    venient
    -0.67
    encers
    -0.65
     Kers
    -0.65
    cow
    -0.65
    POSITIVE LOGITS
    itect
    1.38
    urally
    1.16
     architecture
    1.07
    ural
    1.07
     Architecture
    0.94
     architect
    0.90
     architectures
    0.78
     architectural
    0.77
    Arch
    0.76
     design
    0.76
    Act Density 0.010%

    No Known Activations