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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical spaces and their arrangements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to layout in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     accuser
    -0.75
    Chance
    -0.74
    netflix
    -0.74
    plets
    -0.72
    pir
    -0.69
     Citizen
    -0.67
    govtrack
    -0.67
     Exxon
    -0.66
    emer
    -0.66
    emi
    -0.66
    POSITIVE LOGITS
     layout
    3.60
     layouts
    3.08
     Layout
    2.63
    layout
    2.44
    Layout
    2.41
     spacing
    1.35
     diagram
    1.33
     configuration
    1.29
     setup
    1.26
     diagrams
    1.25
    Act Density 0.020%

    No Known Activations