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

    Neuronpedia

    INDEX
    Explanations

    the presence of structured elements in complex documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.59
    šč
    -0.52
     do
    -0.45
     The
    -0.45
     G
    -0.44
     top
    -0.44
     A
    -0.44
     H
    -0.44
     I
    -0.44
     h
    -0.43
    POSITIVE LOGITS
     Roskov
    1.43
    parsedMessage
    1.15
    numerusform
    1.10
    Geplaatst
    1.08
    UrlResolution
    1.06
     EconPapers
    0.97
    expandindo
    0.96
    rrggbb
    0.94
    SourceChecksum
    0.94
     otomatig
    0.91
    Act Density 0.184%

    No Known Activations