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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations or structures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ward
    -0.16
    Sink
    -0.15
    inker
    -0.15
    aps
    -0.14
    &nbsp
    -0.14
    िà¤ķल
    -0.14
    bate
    -0.14
     Gee
    -0.14
     cray
    -0.14
    \
    -0.13
    POSITIVE LOGITS
    section
    0.26
    document
    0.26
    chapter
    0.22
    begin
    0.21
     document
    0.21
     section
    0.19
    title
    0.19
     chapter
    0.18
    Require
    0.18
    Document
    0.17
    Act Density 0.086%

    No Known Activations