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

    Neuronpedia

    INDEX
    Explanations

    references to spatial positioning and arrangement within a space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chambers
    -0.16
    496
    -0.15
     suites
    -0.15
     dumpsters
    -0.15
     Chamber
    -0.15
     warehouses
    -0.15
     tents
    -0.15
    hone
    -0.14
    ware
    -0.14
    pty
    -0.14
    POSITIVE LOGITS
     shelf
    0.33
     table
    0.33
     counter
    0.31
     mant
    0.28
    shelf
    0.28
     desk
    0.27
     tables
    0.27
    -counter
    0.26
    æ¡Į
    0.26
     shelves
    0.25
    Act Density 0.132%

    No Known Activations