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

    Neuronpedia

    INDEX
    Explanations

    specific codes and technical identifiers

    oai_token-act-pair · gpt-3.5-turbo

    text segments without any visible content (empty segments)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Azerb
    -0.04
    oÄŁ
    -0.03
    ij士
    -0.03
    elsius
    -0.03
     guiActiveUn
    -0.03
    Þ
    -0.03
     Vaugh
    -0.03
     pregn
    -0.03
    £ı
    -0.03
     Canaver
    -0.03
    POSITIVE LOGITS
    ↵
    0.05
    The
    0.05
    -
    0.04
    .
    0.04
    ,
    0.04
    A
    0.04
    In
    0.04
     the
    0.04
    I
    0.04
    <|endoftext|>
    0.04
    Act Density 3.302%

    No Known Activations