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

    Neuronpedia

    INDEX
    Explanations

    adjectives and their use in modifying nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĥĦ
    -0.15
     Bray
    -0.14
    erty
    -0.14
    Ģ
    -0.14
     surroundings
    -0.14
    avage
    -0.14
    ?=
    -0.14
    ifr
    -0.14
    .boost
    -0.13
    zell
    -0.13
    POSITIVE LOGITS
    æİĮ
    0.17
     Corm
    0.14
     attachment
    0.14
    ĥĿ
    0.14
    kip
    0.14
    дж
    0.14
    _DEBUG
    0.13
    ÙĥاÙħ
    0.13
    orm
    0.13
     kort
    0.13
    Act Density 0.014%

    No Known Activations