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

    Neuronpedia

    INDEX
    Explanations

    references to leaked documents and investigative reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abis
    -0.17
     CrossRef
    -0.15
     Announcement
    -0.15
     depletion
    -0.15
     stalk
    -0.15
     anunci
    -0.14
    ignet
    -0.14
    ÐĴÐŀ
    -0.13
    anto
    -0.13
    .qual
    -0.13
    POSITIVE LOGITS
     internal
    0.30
    internal
    0.26
     Internal
    0.26
     tro
    0.25
     obtained
    0.25
     leaked
    0.25
     documents
    0.24
     cache
    0.24
    Internal
    0.24
     emails
    0.24
    Act Density 0.107%

    No Known Activations