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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and operations

    oai_token-act-pair · gpt-3.5-turbo

    closing braces in mathematical or programming expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eworks
    -1.00
    uga
    -0.83
    emark
    -0.83
    ateur
    -0.82
    estone
    -0.79
    sembly
    -0.78
    erek
    -0.78
    assador
    -0.78
    cients
    -0.75
    etimes
    -0.75
    POSITIVE LOGITS
    ··
    0.90
    ({
    0.88
    \)
    0.87
    $$
    0.80
    },
    0.79
    GROUP
    0.76
    âĪĴ
    0.75
    &
    0.74
    âĶĢâĶĢ
    0.74
    ()
    0.73
    Act Density 0.017%

    No Known Activations