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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    大小
    -0.07
    最大化
    -0.07
     believed
    -0.07
    ⚫
    -0.07
     etter
    -0.06
    毗邻
    -0.06
     freaking
    -0.06
    quí
    -0.06
    呼ば
    -0.06
    ➸
    -0.06
    POSITIVE LOGITS
     habit
    0.08
    avatar
    0.07
    胚胎
    0.07
    的年轻人
    0.07
    锻炼
    0.07
    翅
    0.06
     ramp
    0.06
    门槛
    0.06
    “They
    0.06
     Ride
    0.06
    Act Density 0.047%

    No Known Activations