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

    Neuronpedia

    INDEX
    Explanations

    requests or calls for action to bring about change

    oai_token-act-pair · gpt-3.5-turbo

    references to initiatives or motions advocating for change or reform

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )!
    -0.77
    !).
    -0.74
    }.
    -0.69
     ain
    -0.68
    )?
    -0.67
    ?).
    -0.67
     hilar
    -0.66
    !/
    -0.62
    ↵Âł
    -0.61
    )...
    -0.61
    POSITIVE LOGITS
     2019
    0.67
     2020
    0.64
     2021
    0.64
     urgently
    0.63
     contingency
    0.62
     2018
    0.61
     Fiscal
    0.59
     Dover
    0.59
     2024
    0.58
     forthcoming
    0.58
    Act Density 1.591%

    No Known Activations