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

    Neuronpedia

    INDEX
    Explanations

    significant nouns and keywords related to actions or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sag
    -0.16
    vos
    -0.16
    duk
    -0.15
    ãĥĪãĥª
    -0.15
    oppel
    -0.15
    enthal
    -0.15
    RIA
    -0.14
     forn
    -0.14
    ENTER
    -0.14
    earer
    -0.14
    POSITIVE LOGITS
    STYPE
    0.14
    naires
    0.14
    ress
    0.14
    xing
    0.14
    amba
    0.14
    conj
    0.14
     Stub
    0.14
    chk
    0.13
    res
    0.13
    .BigInteger
    0.13
    Act Density 0.006%

    No Known Activations