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

    Neuronpedia

    INDEX
    Explanations

    concerns related to home safety and structural integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    елиÑĩ
    -0.14
     Lo
    -0.14
    Lo
    -0.14
     æĴ
    -0.14
    εÏģμαν
    -0.14
     Cage
    -0.13
    249
    -0.13
    ukan
    -0.13
    <decltype
    -0.13
    scaling
    -0.13
    POSITIVE LOGITS
     basement
    0.33
     Basement
    0.32
    crawl
    0.29
     foundation
    0.28
    foundation
    0.26
     crawl
    0.26
     craw
    0.24
    Foundation
    0.23
     Foundation
    0.22
     Waterproof
    0.22
    Act Density 0.005%

    No Known Activations