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

    Neuronpedia

    INDEX
    Explanations

    the presence of whitespace or formatting characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.54
     validés
    -0.54
    שְׁ
    -0.52
     spéciaux
    -0.51
     suivants
    -0.50
     löyty
    -0.49
    ьаж
    -0.49
     agrícolas
    -0.48
    过来的
    -0.48
    umab
    -0.46
    POSITIVE LOGITS
    </h3>
    0.86
    </td>
    0.86
    </h2>
    0.85
    </em>
    0.84
    </i>
    0.84
    </h5>
    0.83
    </h6>
    0.83
    </h1>
    0.81
    </strong>
    0.80
    </b>
    0.80
    Act Density 0.846%

    No Known Activations