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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical or logical structures related to control systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fé
    -0.75
     Ade
    -0.70
    (.*
    -0.69
     Festi
    -0.69
     Hilde
    -0.69
     Gwend
    -0.69
     Gund
    -0.69
     McCar
    -0.67
     Osw
    -0.66
    brook
    -0.66
    POSITIVE LOGITS
    ″]
    1.46
    })]
    1.41
    "]
    1.39
    }]
    1.39
    ]
    1.35
    ]]
    1.30
    )]
    1.29
     "]
    1.28
    ]}
    1.27
    ])
    1.27
    Act Density 0.188%

    No Known Activations