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

    Neuronpedia

    INDEX
    Explanations

    periods and punctuation-related elements in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    -0.59
    ())))
    -0.52
    ]))
    -0.51
     aDecoder
    -0.50
    ")))
    -0.49
     bParam
    -0.48
    )))
    -0.48
    ]--;
    -0.48
    '));
    -0.47
    ])))
    -0.47
    POSITIVE LOGITS
    脚注の使い方
    0.78
    ⓧ
    0.74
     MessageBoxIcon
    0.69
    Pyx
    0.65
     للمعارف
    0.65
    ViewImports
    0.64
    帖最后由
    0.62
    ectin
    0.62
    dough
    0.61
    AccessorTable
    0.61
    Act Density 0.016%

    No Known Activations