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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific document structure markers like "<bos>"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Koz
    -0.97
    CascadeType
    -0.83
    poin
    -0.79
     لينك
    -0.79
     rhestr
    -0.78
    ufact
    -0.74
    leſs
    -0.74
    Koz
    -0.72
     ISD
    -0.72
    ressee
    -0.72
    POSITIVE LOGITS
    </sup>
    1.44
    </sub>
    1.36
    </u>
    1.23
    </s>
    1.11
    </em>
    1.03
    </i>
    0.96
    </code>
    0.95
     }}
    0.95
    }}
    0.93
    ))
    0.85
    Act Density 0.119%

    No Known Activations