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

    Neuronpedia

    INDEX
    Explanations

    instances of emphasis or hesitation in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ésult
    -0.79
    udadera
    -0.76
    tispiece
    -0.68
    phazard
    -0.67
     Shakspeare
    -0.67
    UGGEST
    -0.66
     tubeless
    -0.66
     Voltaire
    -0.66
     Efq
    -0.66
     Stateless
    -0.66
    POSITIVE LOGITS
    )
    0.68
    </sup>
    0.61
    ）
    0.59
    ...)
    0.59
    ),
    0.59
    ])
    0.57
    ]
    0.57
    ))
    0.56
    ).
    0.56
    mtable
    0.55
    Act Density 0.478%

    No Known Activations