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

    Neuronpedia

    INDEX
    Explanations

    markers of text structure or segmentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </em>
    -0.78
    </td>
    -0.76
    </h6>
    -0.76
    </blockquote>
    -0.76
    </code>
    -0.72
    </i>
    -0.71
    </s>
    -0.70
    </h5>
    -0.70
     …
    -0.70
    </strong>
    -0.67
    POSITIVE LOGITS
     deſt
    0.92
     feroit
    0.89
     pleaſure
    0.87
     fubject
    0.87
     auroit
    0.86
     poffible
    0.85
     beſt
    0.83
     becauſe
    0.83
     myſelf
    0.82
     Monfieur
    0.82
    Act Density 0.267%

    No Known Activations