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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     yö
    -0.07
    绩
    -0.07
     READY
    -0.07
    一件
    -0.07
    ıyorum
    -0.06
    _tok
    -0.06
    小镇
    -0.06
    typeparam
    -0.06
    oord
    -0.06
     BUFF
    -0.06
    POSITIVE LOGITS
     medicine
    0.07
     леч
    0.07
    レーション
    0.07
    _HP
    0.07
    thrown
    0.07
    封
    0.07
     blockers
    0.07
     empire
    0.06
    世界各国
    0.06
    ⾨
    0.06
    Act Density 0.004%

    No Known Activations