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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "root" or foundational elements related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñĩик
    -0.17
    418
    -0.16
    issing
    -0.16
    ichte
    -0.16
    hare
    -0.15
    176
    -0.15
    achts
    -0.14
    ØŃداث
    -0.14
    atar
    -0.14
    ous
    -0.14
    POSITIVE LOGITS
    /root
    0.28
    kits
    0.26
    stock
    0.25
    stocks
    0.25
    beer
    0.24
    (ROOT
    0.24
    =root
    0.22
     Root
    0.21
     root
    0.21
    -root
    0.20
    Act Density 0.016%

    No Known Activations