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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    smaller
    0.79
    significant
    0.73
    Smaller
    0.72
    دى
    0.71
    substantial
    0.71
    ął
    0.70
    project
    0.69
    <0x0D>
    0.68
    </tr>
    0.68
    Cornell
    0.67
    POSITIVE LOGITS
     puns
    0.91
     goddesses
    0.89
     invariants
    0.88
     adoration
    0.88
     hiatus
    0.88
     slogans
    0.87
     skies
    0.86
     blushed
    0.85
     monsters
    0.84
     chromosomes
    0.84
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.