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

    Neuronpedia

    INDEX
    Explanations

    headings and structural elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.86
    StructEnd
    -0.84
    AsUp
    -0.83
    Eksteraj
    -0.82
     AssemblyCulture
    -0.81
    хьтан
    -0.81
    windowFixed
    -0.81
    Tikang
    -0.80
    SharedDtor
    -0.78
    getDescriptor
    -0.77
    POSITIVE LOGITS
    (
    0.63
    “
    0.62
    ↵↵↵↵
    0.61
    [
    0.59
    <strong>
    0.57
    <h1>
    0.56
    <h2>
    0.54
    ↵
    0.54
    ↵↵↵
    0.54
    {
    0.54
    Act Density 0.003%

    No Known Activations