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

    Neuronpedia

    INDEX
    Explanations

    references to clusters and their components in a data storage context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    o
    -0.17
    edor
    -0.16
    oge
    -0.16
    _UNS
    -0.15
    oke
    -0.15
    e
    -0.15
    oom
    -0.15
    emin
    -0.15
     Gentle
    -0.15
    ox
    -0.15
    POSITIVE LOGITS
    ustering
    0.23
    USTER
    0.22
    ASSES
    0.20
    usters
    0.20
    airs
    0.20
    arend
    0.20
    erator
    0.19
    ipse
    0.19
    avier
    0.18
    ément
    0.18
    Act Density 0.020%

    No Known Activations