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

    Neuronpedia

    INDEX
    Explanations

    initial tokens indicating the start of a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’
    -0.46
     lu
    -0.44
    .
    -0.42
    ▲
    -0.41
     ***
    -0.41
    Lu
    -0.41
    “
    -0.40
    【
    -0.40
     Lu
    -0.40
     HZ
    -0.40
    POSITIVE LOGITS
     AssemblyCulture
    0.96
    GEBURTSDATUM
    0.85
     AssemblyCompany
    0.71
     autorytatywna
    0.66
     ſeveral
    0.65
    Демографія
    0.64
    ftagPool
    0.64
     виправивши
    0.63
    RenderAtEndOf
    0.60
    transQ
    0.59
    Act Density 0.712%

    No Known Activations