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

    Neuronpedia

    INDEX
    Explanations

    numerical listings within text, such as bullet points or itemized sections

    oai_token-act-pair · gpt-3.5-turbo

    numerical sequences and structured list-like data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agre
    -0.76
     hog
    -0.68
    cius
    -0.67
    akeru
    -0.66
     seiz
    -0.66
    merce
    -0.65
    wagen
    -0.64
    krit
    -0.64
    cies
    -0.63
     corrid
    -0.62
    POSITIVE LOGITS
    ][
    1.10
    ].
    1.09
    ]).
    1.04
    ]
    1.02
    ],
    0.98
    ]),
    0.91
    ];
    0.90
     ].
    0.88
    ])
    0.87
     ]
    0.85
    Act Density 0.037%

    No Known Activations