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

    Neuronpedia

    INDEX
    Explanations

    references to sections and propositions in a formal document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eza
    -0.16
    reau
    -0.15
    readcr
    -0.15
    овоÑĢ
    -0.14
    jedn
    -0.14
    ertest
    -0.14
    <quote
    -0.14
    CCI
    -0.14
    /WebAPI
    -0.14
    ä¸į好
    -0.14
    POSITIVE LOGITS
     ref
    0.26
     Ref
    0.24
     papers
    0.23
     [
    0.23
     refs
    0.22
     paper
    0.22
     references
    0.19
     Paper
    0.19
     works
    0.19
     Section
    0.17
    Act Density 0.074%

    No Known Activations