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

    Neuronpedia

    INDEX
    Explanations

    mathematical or logical expressions and relationships within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </i>
    -0.81
    </b>
    -0.77
    '))
    -0.75
    ',
    -0.73
    ')}}
    -0.67
    <b>
    -0.65
    '));
    -0.63
    '});
    -0.63
    )',
    -0.60
    ’,
    -0.60
    POSITIVE LOGITS
    """
    1.95
     """
    1.58
    ."""
    1.39
    """
    1.35
     """
    1.09
    """.
    1.09
    """,
    1.08
    """"
    1.05
    </h4>
    0.97
    """)
    0.96
    Act Density 0.870%

    No Known Activations