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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to reporting, news, and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContentAlignment
    -0.12
    .LogWarning
    -0.12
    ¾
    -0.11
     Benedict
    -0.11
     Bernard
    -0.11
    287
    -0.11
    ¼
    -0.11
    âĢ¦↵
    -0.11
    >{"
    -0.11
    ĵ¨
    -0.11
    POSITIVE LOGITS
    /Gate
    0.15
     ÑĦÑĥнда
    0.14
    udeau
    0.14
     ëĦ¤ìĿ´íĬ¸
    0.13
    ngo
    0.13
    gebn
    0.13
    нам
    0.13
    jom
    0.13
     hrd
    0.13
    UrlParser
    0.12
    Act Density 0.013%

    No Known Activations