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

    Neuronpedia

    INDEX
    Explanations

    terms and acronyms related to exclusions or exceptions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azzo
    -0.16
    byname
    -0.15
     seeding
    -0.15
     Rouge
    -0.15
    496
    -0.14
    ani
    -0.14
    noon
    -0.14
    nap
    -0.14
    inals
    -0.14
    iani
    -0.13
    POSITIVE LOGITS
    elles
    0.17
    eyin
    0.16
    reck
    0.16
    dem
    0.15
    Dem
    0.14
    raq
    0.14
    eed
    0.14
    mo
    0.14
    udem
    0.14
    omba
    0.14
    Act Density 0.035%

    No Known Activations