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

    Neuronpedia

    INDEX
    Explanations

    content related to legal or political discourse

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal or regulatory issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Published
    -0.59
     Originally
    -0.51
     pictured
    -0.50
    regor
    -0.49
    isbury
    -0.48
     IMAGES
    -0.48
     Formula
    -0.47
     Latest
    -0.47
     âĢº
    -0.47
    ricanes
    -0.46
    POSITIVE LOGITS
    )).
    1.13
    ]."
    1.09
    )."
    1.08
    ).[
    1.01
    ]).
    0.94
    .).
    0.91
    .'"
    0.86
    %).
    0.85
    }.
    0.84
    ))))
    0.82
    Act Density 3.616%

    No Known Activations