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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     thin
    1.24
     ancienne
    1.11
     pago
    1.00
    ஜ
    0.99
     Absolute
    0.98
     nonché
    0.97
     literally
    0.97
    ገድ
    0.96
     cabo
    0.94
     打
    0.94
    POSITIVE LOGITS
    🏻
    1.58
    م
    1.48
    но
    1.47
    🏼
    1.45
    مپ
    1.42
    رہ
    1.40
    ted
    1.40
    hyung
    1.36
    ことを
    1.35
     voldoende
    1.34
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.