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

    Neuronpedia

    INDEX
    Explanations

    function calls related to setting properties and updating layout configurations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming syntax and method calls, particularly in Java or similar object-oriented programming languages.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    <unused28>
    -1.41
    <unused14>
    -1.41
    <unused52>
    -1.41
    <unused79>
    -1.41
    <unused68>
    -1.41
    <unused16>
    -1.40
    <unused23>
    -1.40
    <unused8>
    -1.40
    [@BOS@]
    -1.40
    <unused3>
    -1.40
    POSITIVE LOGITS
     donc
    0.28
     thus
    0.27
    D
    0.26
     therefore
    0.24
    S
    0.23
    C
    0.23
     then
    0.23
    G
    0.22
    1
    0.22
    3
    0.22
    Act Density 0.125%

    No Known Activations