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

    Neuronpedia

    INDEX
    Explanations

    percentages or proportions stated in text

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and percentages relating to demographics or survey results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.82
     ."
    -0.56
     disapp
    -0.55
    izoph
    -0.55
     satell
    -0.54
    etheless
    -0.53
    awaru
    -0.52
     compr
    -0.50
    foreseen
    -0.50
    oro
    -0.49
    POSITIVE LOGITS
    ),
    1.78
    ),"
    1.76
    )
    1.75
    ):
    1.72
    %)
    1.71
    )—
    1.64
    )."
    1.58
    )/
    1.58
    )...
    1.56
    );
    1.56
    Act Density 0.171%

    No Known Activations