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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the beginning of new sections or topics within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.90
    PreferredItem
    -0.86
     TextInputType
    -0.84
    mybatisplus
    -0.84
    expandindo
    -0.83
     Efq
    -0.83
    InjectAttribute
    -0.83
    Portail
    -0.83
    parsedMessage
    -0.82
    AnchorStyles
    -0.82
    POSITIVE LOGITS
    </em>
    0.92
    </i>
    0.77
    </u>
    0.72
    "
    0.69
    </code>
    0.65
    ...
    0.64
     ...
    0.61
    ","
    0.56
      
    0.55
     
    0.54
    Act Density 0.308%

    No Known Activations