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

    Neuronpedia

    INDEX
    Explanations

    examples of legal terminology or concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant cases or notable statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )",
    -0.67
    romy
    -0.63
    "],"
    -0.63
    ],"
    -0.59
    )].
    -0.58
     med
    -0.58
    "},"
    -0.58
     )]
    -0.57
    .","
    -0.55
    ]"
    -0.55
    POSITIVE LOGITS
    surprisingly
    0.81
    Plus
    0.71
    prisingly
    0.71
    mmm
    0.67
    Sounds
    0.66
    ogether
    0.65
    icularly
    0.65
     Thoughts
    0.64
     Stuff
    0.62
     Names
    0.62
    Act Density 0.473%

    No Known Activations