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

    Neuronpedia

    INDEX
    Explanations

    references to news articles and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ('
    -0.58
    fır
    -0.49
    ("
    -0.48
    that
    -0.46
    •
    -0.45
    rest
    -0.44
     drivers
    -0.44
    const
    -0.42
     namelijk
    -0.42
    Make
    -0.42
    POSITIVE LOGITS
    gnition
    0.82
    Geplaatst
    0.82
    istoitu
    0.80
    DeleteBehavior
    0.78
     Paglinawan
    0.76
     تضيفلها
    0.74
     Consultado
    0.72
    MemoryWarning
    0.71
    Diweddarwch
    0.71
    ]").
    0.70
    Act Density 0.047%

    No Known Activations