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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and structured data definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused63>
    -0.55
     ...
    -0.54
    ↵
    -0.54
    <unused60>
    -0.53
     …
    -0.51
     CreateTagHelper
    -0.51
    <unused61>
    -0.51
    ↵↵
    -0.50
    \\\
    -0.49
    ................
    -0.48
    POSITIVE LOGITS
    +#+#
    1.05
    ########.
    1.05
    0.98
     Waray
    0.96
     kasarigan
    0.95
    verwijspagina
    0.89
    :+:
    0.86
    AndEndTag
    0.83
     referenties
    0.81
    脚注の使い方
    0.80
    Act Density 0.248%

    No Known Activations