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

    Neuronpedia

    INDEX
    Explanations

    terms related to architecture and architects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to architecture and architects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TPS
    -0.74
    eworthy
    -0.72
    mma
    -0.67
    zees
    -0.66
    othal
    -0.66
    cow
    -0.64
    ties
    -0.62
    awar
    -0.62
    "]=>
    -0.62
    Redd
    -0.61
    POSITIVE LOGITS
    urally
    1.60
    itect
    1.34
    ural
    1.30
     architect
    1.01
     architects
    0.90
     architectural
    0.83
     Architecture
    0.80
     Architects
    0.80
     Architect
    0.80
    urated
    0.78
    Act Density 0.074%

    No Known Activations