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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific placeholder tokens indicating structured data or comments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.73
    ophi
    -0.63
     Stall
    -0.63
     vocales
    -0.62
    KommentareTeilen
    -0.61
     Hage
    -0.60
     Nabi
    -0.60
    ètres
    -0.59
    libft
    -0.58
     costumi
    -0.58
    POSITIVE LOGITS
    </th>
    0.84
     StatelessWidget
    0.82
    </h2>
    0.79
    </i>
    0.70
    </h5>
    0.70
    \{\\
    0.70
    AndEndTag
    0.69
    </h6>
    0.69
    </b>
    0.67
    </h4>
    0.67
    Act Density 0.049%

    No Known Activations