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

    Neuronpedia

    INDEX
    Explanations

    various types of content-related structures in documents, such as titles, sections, and categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ùa
    -0.17
    ÙĦÙĬÙĩ
    -0.16
    MU
    -0.15
    nodoc
    -0.15
    lite
    -0.14
    ummies
    -0.14
    _tE
    -0.14
    лоÑĩ
    -0.14
    /gtest
    -0.14
    atform
    -0.14
    POSITIVE LOGITS
    oft
    0.16
    \Context
    0.15
    ichen
    0.15
    kle
    0.14
    оÑĤи
    0.14
    ount
    0.13
    azen
    0.13
    ké
    0.13
    riott
    0.13
    odge
    0.13
    Act Density 0.425%

    No Known Activations