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

    Neuronpedia

    INDEX
    Explanations

    categories and classifications within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]))
    -0.95
     "'");
    -0.90
    ")));
    -0.88
     ''
    -0.87
    }))
    -0.86
    </>
    -0.82
    ]));
    -0.81
    ']?>
    -0.76
    )");
    -0.72
    ]);
    -0.72
    POSITIVE LOGITS
     category
    2.20
     categories
    2.07
     Category
    1.89
     CATEGORY
    1.85
    categories
    1.83
    category
    1.81
     Categories
    1.80
     getCategory
    1.74
    CATEGORY
    1.72
    Category
    1.67
    Act Density 0.104%

    No Known Activations