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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and their simplification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )))),
    -1.08
    )))))
    -0.95
    ())))
    -0.92
    ))),
    -0.88
    ())),
    -0.87
    ))^
    -0.87
    ))))
    -0.85
    ']))
    -0.85
     дописавши
    -0.83
    ])))
    -0.82
    POSITIVE LOGITS
    </strong>
    0.93
    </b>
    0.82
    </h2>
    0.72
    </u>
    0.67
     betweenstory
    0.64
     فريبيس
    0.64
     GenerationType
    0.64
    </em>
    0.62
     ProtoMessage
    0.62
    +#+#
    0.60
    Act Density 5.439%

    No Known Activations