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

    Neuronpedia

    INDEX
    Explanations

    references to various types of "discs" and disc-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    703
    -0.15
    chie
    -0.15
    kad
    -0.15
    itably
    -0.15
    uty
    -0.15
    itest
    -0.15
    ami
    -0.14
    çĵľ
    -0.14
    combe
    -0.14
    itz
    -0.14
    POSITIVE LOGITS
    ursive
    0.23
    arding
    0.22
    /disc
    0.21
    ography
    0.19
    ussions
    0.19
    loses
    0.19
    -disc
    0.19
    ourses
    0.19
    losures
    0.18
     Disc
    0.18
    Act Density 0.023%

    No Known Activations