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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of names, years, and other structured data such as dates and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.71
     (?,
    -0.66
    ciplinary
    -0.65
    ——
    -0.57
    laim
    -0.56
     [/
    -0.56
    enance
    -0.55
    uten
    -0.53
    ifference
    -0.53
    ãĢIJ
    -0.53
    POSITIVE LOGITS
    ).
    1.40
    ?).
    1.35
    )."
    1.35
    !).
    1.34
    +)
    1.29
    ),
    1.24
    !),
    1.23
    )
    1.20
    %).
    1.19
    .).
    1.18
    Act Density 0.290%

    No Known Activations