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

    Neuronpedia

    INDEX
    Explanations

    numbers and financial values

    oai_token-act-pair · gpt-3.5-turbo

    references to animated films or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.94
    etheless
    -0.60
    ãĢİ
    -0.57
    ":[{"
    -0.51
    ãĢIJ
    -0.50
    Newsletter
    -0.48
     showc
    -0.47
    ADVERTISEMENT
    -0.46
    âĶĢâĶĢâĶĢâĶĢ
    -0.46
    Published
    -0.46
    POSITIVE LOGITS
    ),"
    2.08
    )?
    2.06
    )
    2.06
    ),
    2.03
    )."
    2.03
    ?)
    2.02
    )"
    2.00
    ?),
    1.98
    ?).
    1.98
    ).
    1.96
    Act Density 1.203%

    No Known Activations