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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of authority and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    رÙĪØ·
    -0.16
    ening
    -0.15
    /sm
    -0.15
    Offsets
    -0.14
    mie
    -0.14
    ERCHANT
    -0.14
    warz
    -0.13
    IZATION
    -0.13
    ุà¸Ļ
    -0.13
    -redux
    -0.13
    POSITIVE LOGITS
    ship
    0.20
        ↵    ↵
    0.18
    fully
    0.17
    ful
    0.16
    anas
    0.16
    zed
    0.16
    ries
    0.15
    ough
    0.15
    ies
    0.15
     Merr
    0.15
    Act Density 0.020%

    No Known Activations