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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal affection and engagement with content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Furn
    -0.17
    lob
    -0.14
    ever
    -0.14
    æĸĹ
    -0.14
     Gordon
    -0.14
    andra
    -0.14
     verk
    -0.14
    416
    -0.14
     Cod
    -0.14
     Fleet
    -0.13
    POSITIVE LOGITS
     slic
    0.18
    iju
    0.15
    annis
    0.14
    огод
    0.14
    assen
    0.14
    anas
    0.14
    graf
    0.14
    หา
    0.14
    ilen
    0.14
    .shiro
    0.14
    Act Density 0.085%

    No Known Activations