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

    Neuronpedia

    INDEX
    Explanations

    references to the construction and building of various structures and facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Antique
    -0.18
     togg
    -0.17
    frog
    -0.15
    زار
    -0.15
     antique
    -0.14
    iero
    -0.14
    ãĤ·ãĥ¼
    -0.13
    DOMNode
    -0.13
    ocop
    -0.13
     ÅŁer
    -0.13
    POSITIVE LOGITS
     facility
    0.28
     build
    0.27
     building
    0.26
    build
    0.24
     facilities
    0.24
     builds
    0.23
     project
    0.22
    .build
    0.22
    -build
    0.22
     new
    0.21
    Act Density 0.295%

    No Known Activations