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

    Neuronpedia

    INDEX
    Explanations

    features related to architectural and structural details of buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    axe
    -0.16
    елиÑĩ
    -0.15
    огод
    -0.15
    .Reporting
    -0.14
    ewidth
    -0.14
    /stdc
    -0.14
    éĶ¦
    -0.14
     Kay
    -0.14
    ứa
    -0.13
    UseProgram
    -0.13
    POSITIVE LOGITS
     basement
    0.31
     foundation
    0.30
    crawl
    0.29
     crawl
    0.29
     Basement
    0.28
     craw
    0.27
     Foundation
    0.25
    foundation
    0.25
     Waterproof
    0.24
     footer
    0.24
    Act Density 0.006%

    No Known Activations