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

    Neuronpedia

    INDEX
    Explanations

    references to dependency or reliance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    smith
    -0.18
    orp
    -0.17
    isations
    -0.16
    lette
    -0.15
    orz
    -0.15
    ordo
    -0.15
    ween
    -0.15
    anooga
    -0.15
    izontally
    -0.14
     leng
    -0.14
    POSITIVE LOGITS
    lessly
    0.19
    ulfilled
    0.17
     upon
    0.16
    ehir
    0.16
     äºİ
    0.15
    .uf
    0.15
    éł¼
    0.15
    лам
    0.15
    <|begin_of_text|>
    0.15
     rely
    0.15
    Act Density 0.016%

    No Known Activations