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

    Neuronpedia

    INDEX
    Explanations

    computer code snippets

    oai_token-act-pair · gpt-3.5-turbo

    references to computer code or error messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compliment
    -0.78
     designs
    -0.69
     cartoons
    -0.68
    asha
    -0.65
     drafting
    -0.64
     drafts
    -0.63
     infographic
    -0.62
    ï¸ı
    -0.62
    rosse
    -0.62
    âĢ¢âĢ¢
    -0.62
    POSITIVE LOGITS
     000000
    1.29
     00000000
    1.16
     ERROR
    1.11
     0000
    1.06
    000000
    1.05
     fixme
    1.04
    00007
    1.02
     Error
    1.01
     ACPI
    1.00
    Disable
    0.99
    Act Density 0.211%

    No Known Activations