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

    Neuronpedia

    INDEX
    Explanations

    references to additional related content or information within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to charts, graphs, and other data visualizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mahjong
    -0.69
    ãĢIJ
    -0.64
    ersive
    -0.61
    wcs
    -0.61
     imperson
    -0.60
     (?,
    -0.60
     guiName
    -0.59
     SERV
    -0.59
     Starcraft
    -0.58
    olerance
    -0.54
    POSITIVE LOGITS
    ).
    1.52
    )).
    1.48
    )."
    1.45
    )—
    1.38
     ).
    1.38
    ]).
    1.38
    .).
    1.34
    ?).
    1.29
    ),
    1.29
    )}
    1.27
    Act Density 0.181%

    No Known Activations