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

    Neuronpedia

    INDEX
    Explanations

    sections and subsections in structured documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.73
     var
    -0.62
    т
    -0.61
     Wint
    -0.61
    .
    -0.60
     (
    -0.58
    //
    -0.57
    起
    -0.56
    ENDIAN
    -0.56
     +
    -0.56
    POSITIVE LOGITS
    subsection
    2.43
    subsubsection
    1.99
     myſelf
    1.29
     himſelf
    1.24
    BibitemShut
    1.24
     autorytatywna
    1.23
     itſelf
    1.22
     raiſ
    1.19
     Jefus
    1.13
     nakalista
    1.11
    Act Density 0.036%

    No Known Activations