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

    Neuronpedia

    INDEX
    Explanations

    words associated with capability or potential, particularly those ending in 'able'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ing
    -0.15
    _literals
    -0.15
    icals
    -0.14
    osphere
    -0.14
    IDEO
    -0.14
    etr
    -0.14
    ed
    -0.14
     ä¹
    -0.14
    arily
    -0.14
    elay
    -0.14
    POSITIVE LOGITS
    heid
    0.18
    /controller
    0.17
    zell
    0.15
    ummings
    0.15
    -bodied
    0.15
    thing
    0.15
    yı
    0.14
    _OVERRIDE
    0.14
     »↵↵
    0.14
    arium
    0.14
    Act Density 0.116%

    No Known Activations