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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     extravagant
    0.52
     wher
    0.52
     nerdy
    0.50
    Ꮯ
    0.49
     consciously
    0.49
     kdo
    0.48
     arise
    0.48
    0.48
    𝕌
    0.48
    𝒑
    0.48
    POSITIVE LOGITS
     അരി
    0.50
    uš
    0.48
    ürz
    0.46
    ö
    0.45
     ihrer
    0.45
    gebung
    0.45
     unserem
    0.44
    Basis
    0.44
    ăz
    0.44
    ässig
    0.44
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.