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

    Neuronpedia

    INDEX
    Explanations

    categories or classifications within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]))
    -0.85
     ''
    -0.78
    ")));
    -0.74
     otomatig
    -0.72
     "'");
    -0.69
    ]));
    -0.68
    }))
    -0.66
     '',
    -0.65
    omla
    -0.64
     смо
    -0.62
    POSITIVE LOGITS
     getCategory
    1.51
     category
    1.49
     categories
    1.36
     CATEGORY
    1.32
     Category
    1.31
    categories
    1.29
     Categories
    1.23
    category
    1.22
    getCategory
    1.17
    CATEGORY
    1.17
    Act Density 0.098%

    No Known Activations