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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, possibly celebrities

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly in entertainment or notable contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -1.12
     [/
    -0.74
    [/
    -0.72
    ãĢİ
    -0.66
     '.
    -0.64
    iencies
    -0.62
    ãĢIJ
    -0.62
    âķIJâķIJ
    -0.61
     [];
    -0.61
    è¦ļéĨĴ
    -0.60
    POSITIVE LOGITS
    )
    1.53
    )"
    1.38
    ),"
    1.38
    )—
    1.36
    !)
    1.35
    ),
    1.33
    )."
    1.33
    )/
    1.33
    ):
    1.32
    )!
    1.31
    Act Density 0.499%

    No Known Activations