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

    Neuronpedia

    INDEX
    Explanations

    the presence of formatting or structural elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.98
     CURIAM
    -0.95
     nakalista
    -0.91
    WithIOException
    -0.82
     تضيفلها
    -0.76
    bited
    -0.76
     Савезне
    -0.75
    GraphicsUnit
    -0.73
     كومونز
    -0.72
    LogFactory
    -0.72
    POSITIVE LOGITS
    ↵↵
    0.92
    <eos>
    0.89
    ↵↵↵
    0.61
    }}}}
    0.56
    ↵
    0.55
    ↵↵↵↵
    0.54
    </table>
    0.53
    ↵↵↵↵↵
    0.52
     umane
    0.51
    ↵↵↵↵↵↵
    0.48
    Act Density 0.088%

    No Known Activations