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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Poker
    0.46
    Gener
    0.45
    GPUs
    0.44
    GraphQL
    0.43
     aparel
    0.43
     Judo
    0.43
    Story
    0.42
    Zombie
    0.42
    Jessica
    0.41
     Livre
    0.41
    POSITIVE LOGITS
    нави
    0.53
    ִ
    0.45
    嚀
    0.44
    ulation
    0.43
    vori
    0.43
    ଭ
    0.42
     pursued
    0.42
    できます
    0.41
     анти
    0.40
    払
    0.40
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.