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

    Neuronpedia

    INDEX
    Explanations

    dates in different formats such as day, month, and year

    oai_token-act-pair · gpt-3.5-turbo

    numerical identifiers or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trucks
    -0.61
     hog
    -0.61
     scenery
    -0.61
     truck
    -0.59
     modelling
    -0.59
    anooga
    -0.59
     cho
    -0.58
     leve
    -0.58
     bulldo
    -0.58
     levers
    -0.57
    POSITIVE LOGITS
    ][
    1.62
    ]
    1.60
    ]"
    1.44
    ],[
    1.38
    ]).
    1.38
    ]}
    1.36
    ])
    1.35
    ].
    1.34
    ]),
    1.29
    ]'
    1.29
    Act Density 0.039%

    No Known Activations