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

    Neuronpedia

    INDEX
    Explanations

    unique identifiers or symbols within a programming or coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſche
    -0.80
     houſe
    -0.73
     purpoſe
    -0.66
     itſelf
    -0.63
     faſt
    -0.62
     Lég
    -0.62
    sonder
    -0.62
    ••••
    -0.62
     multiplic
    -0.61
     anom
    -0.60
    POSITIVE LOGITS
    </sub>
    3.22
    </sup>
    1.62
    </s>
    1.34
    </h6>
    1.16
    </code>
    1.10
     }}$
    1.09
    </caption>
    0.98
    </th>
    0.94
    </i>
    0.92
    ParallelGroup
    0.88
    Act Density 0.136%

    No Known Activations