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

    Neuronpedia

    INDEX
    Explanations

    dates in historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seams
    -0.74
     lobb
    -0.65
     trophies
    -0.64
     roofs
    -0.61
     noses
    -0.61
     tongues
    -0.60
     streaks
    -0.59
     setting
    -0.59
     nose
    -0.59
     balcon
    -0.58
    POSITIVE LOGITS
    ]
    1.11
    ][
    1.07
    ]).
    1.01
    ]"
    0.97
    ].
    0.93
    ],[
    0.92
    ]:
    0.91
    ])
    0.90
    ]),
    0.85
    ];
    0.85
    Act Density 0.038%

    No Known Activations