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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs indicated by unique tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elemField
    -0.68
    SharedCtor
    -0.67
    rxjs
    -0.67
    UrlResolution
    -0.67
    StoryboardSegue
    -0.66
     "--
    -0.66
    LoggerFactory
    -0.65
     Diener
    -0.64
     jScrollPane
    -0.64
    protoc
    -0.64
    POSITIVE LOGITS
    ↵↵
    0.98
    <eos>
    0.89
    expandindo
    0.58
     vectorielles
    0.57
    <tr>
    0.52
     aufgestellt
    0.52
    ↵↵↵
    0.51
    </table>
    0.51
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.49
    <h2>
    0.49
    Act Density 0.052%

    No Known Activations