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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    6
    0.88
    Steps
    0.80
    4
    0.80
    ↵
    0.80
    <unused60>
    0.79
    .
    0.79
    ORIAL
    0.78
     Steps
    0.75
    0
    0.75
    8
    0.74
    POSITIVE LOGITS
    𝓑
    0.92
     opi
    0.90
    椃
    0.89
     Thanos
    0.89
     Coinbase
    0.88
     shinobi
    0.86
     progen
    0.86
    ंतिक
    0.86
    𝓈
    0.86
     balsamic
    0.84
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.