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

    Neuronpedia

    INDEX
    Explanations

    references to lists and related organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ListOf
    -0.19
     listed
    -0.18
    List
    -0.18
    istas
    -0.16
    _list
    -0.16
     listings
    -0.15
    lest
    -0.15
    steen
    -0.15
    zan
    -0.15
    lush
    -0.15
    POSITIVE LOGITS
    eners
    0.30
    ings
    0.29
    icle
    0.28
    ened
    0.27
    -unstyled
    0.24
    icles
    0.23
    agem
    0.23
    ening
    0.23
    owel
    0.22
    rik
    0.20
    Act Density 0.063%

    No Known Activations