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

    Neuronpedia

    INDEX
    Explanations

    references to architectural structures and their historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     control
    -0.48
     
    -0.47
    Control
    -0.46
    ↵
    -0.46
     Control
    -0.44
    field
    -0.42
    Гру
    -0.41
     to
    -0.41
     (
    -0.41
     t
    -0.41
    POSITIVE LOGITS
     towers
    1.35
     tower
    1.30
     tallest
    1.25
     TOWER
    1.19
     skyscrapers
    1.16
    tower
    1.16
     skyscraper
    1.14
    towers
    1.13
     betweenstory
    1.13
    RenderAtEndOf
    1.10
    Act Density 0.254%

    No Known Activations