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

    Neuronpedia

    INDEX
    Explanations

    instructions related to physical movements or positions in an exercise context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    closedir
    -0.61
     Himo
    -0.50
    uldron
    -0.45
    zarchiwizowane
    -0.45
    bitol
    -0.44
    WebVitals
    -0.43
    Stepping
    -0.43
     depan
    -0.43
    ENSIONS
    -0.42
    kasten
    -0.41
    POSITIVE LOGITS
     crawling
    0.84
     crawled
    0.80
     lying
    0.79
     Lying
    0.78
     crawl
    0.74
     crawls
    0.73
    TypedDataSet
    0.72
     Craw
    0.70
    craw
    0.69
     Pillow
    0.69
    Act Density 0.160%

    No Known Activations