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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ！");↵
    -0.08
     wides
    -0.08
     foe
    -0.07
    击杀
    -0.07
    bitset
    -0.07
    _EVENTS
    -0.07
    檞
    -0.07
     headlines
    -0.07
     Natalie
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    为人
    0.07
    LAB
    0.07
     indoor
    0.06
    .ud
    0.06
    job
    0.06
    的热情
    0.06
    omatic
    0.06
    茶
    0.06
    פנים
    0.06
    为大家
    0.06
    Act Density 0.001%

    No Known Activations