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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ſſung
    -1.14
    rbrakk
    -1.13
    tagHelperRunner
    -1.10
    [@BOS@]
    -1.09
    mpagne
    -1.09
    <unused52>
    -1.09
    <unused79>
    -1.09
    <unused74>
    -1.09
    <unused14>
    -1.09
    <unused41>
    -1.09
    POSITIVE LOGITS
    <td>
    0.72
    The
    0.53
    [toxicity=0]
    0.45
    <th>
    0.45
    <strong>
    0.45
    (
    0.45
    _
    0.44
    hline
    0.43
    -
    0.43
    </tr>
    0.42
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.