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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    273
    -0.15
    sher
    -0.14
    KEN
    -0.14
    iken
    -0.14
    251
    -0.13
    753
    -0.13
     ör
    -0.13
    elle
    -0.12
    lesi
    -0.12
    etter
    -0.12
    POSITIVE LOGITS
     ÙħØŃ
    0.15
    undy
    0.14
    iland
    0.14
    /runtime
    0.14
     condition
    0.14
    ":"'
    0.13
    нин
    0.13
    deaux
    0.13
    ersiz
    0.13
    isol
    0.13
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.