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

    Neuronpedia

    INDEX
    Explanations

    titles or headings containing acronyms or abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    references to media content or headlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.91
    iencies
    -0.79
     };
    -0.75
     [/
    -0.75
     [...]
    -0.74
    "},
    -0.72
    [/
    -0.71
    conservancy
    -0.71
    etheless
    -0.66
     [âĢ¦]
    -0.65
    POSITIVE LOGITS
    )"
    1.51
    )
    1.42
    )/
    1.40
    )--
    1.32
    )]
    1.32
    )-
    1.29
    )(
    1.28
    *)
    1.27
    ):
    1.25
    ),"
    1.24
    Act Density 0.165%

    No Known Activations