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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .and
    -0.08
    GameOver
    -0.08
     --↵
    -0.07
    mozilla
    -0.07
    >--
    -0.07
     movers
    -0.07
     Hungary
    -0.07
    环境保护
    -0.07
    etadata
    -0.07
     إليه
    -0.07
    POSITIVE LOGITS
    .Tables
    0.06
     הזוג
    0.06
    _EOL
    0.06
    储蓄
    0.06
     winter
    0.06
     BTC
    0.06
    了不少
    0.06
     WATCH
    0.06
     splitting
    0.06
    ivable
    0.06
    Act Density 0.001%

    No Known Activations