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

    Neuronpedia

    INDEX
    Explanations

    scientific notation or mathematical variables and constants associated with formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </td>
    -0.81
    MigrationBuilder
    -0.81
    </h5>
    -0.78
    </em>
    -0.78
    </h6>
    -0.78
    </i>
    -0.77
    </th>
    -0.76
    </h4>
    -0.75
    ↵
    -0.73
    </h2>
    -0.71
    POSITIVE LOGITS
     pleaſure
    0.96
     greateſt
    0.91
     Eſ
    0.88
     للاسماء
    0.86
     beſt
    0.85
    rawDesc
    0.85
    altezza
    0.83
     wikipagina
    0.80
     deſt
    0.80
    valently
    0.79
    Act Density 0.279%

    No Known Activations