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

    Neuronpedia

    INDEX
    Explanations

    phrases related to formal announcements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    the word "For"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiz
    -0.73
     crawl
    -0.64
     forg
    -0.62
    zona
    -0.58
     eh
    -0.57
     looms
    -0.56
     bottleneck
    -0.56
     jaws
    -0.55
    chenko
    -0.55
    adr
    -0.54
    POSITIVE LOGITS
    bidden
    1.52
    gotten
    1.50
    ced
    1.24
    cing
    1.19
    give
    1.15
     example
    1.12
    bes
    1.08
    wards
    1.06
     instance
    1.05
    getting
    1.02
    Act Density 0.061%

    No Known Activations