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

    Neuronpedia

    INDEX
    Explanations

    terms related to architecture and specific buildings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     kram
    -0.85
     stoff
    -0.85
     kosme
    -0.80
     makro
    -0.79
     kriminal
    -0.76
     kompati
    -0.76
     subjek
    -0.75
     alkoh
    -0.75
     akut
    -0.75
     krab
    -0.74
    POSITIVE LOGITS
     architectural
    0.76
     architects
    0.73
     architect
    0.72
     Designers
    0.67
     design
    0.65
     Planners
    0.64
     Architects
    0.64
     Architectural
    0.62
     designers
    0.61
     Buildings
    0.60
    Act Density 0.618%

    No Known Activations