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

    Neuronpedia

    INDEX
    Explanations

    code-related constructs and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.88
    parsedMessage
    -0.77
    expandindo
    -0.77
    帖最后由
    -0.77
    脚注の使い方
    -0.74
     kasarigan
    -0.74
    ſelf
    -0.72
    SerializedName
    -0.70
    出版年
    -0.70
     Савезне
    -0.69
    POSITIVE LOGITS
    <eos>
    0.60
    ↵↵
    0.48
    Phew
    0.48
    Whew
    0.47
    .
    0.46
    if
    0.45
    pann
    0.44
    </table>
    0.43
    ↵
    0.42
     exhausted
    0.42
    Act Density 0.310%

    No Known Activations