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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    olg
    -0.08
    nde
    -0.07
    桌子
    -0.07
     Vegetable
    -0.07
    老子
    -0.07
    enas
    -0.07
     Tent
    -0.07
    唑
    -0.07
    engo
    -0.06
    塞
    -0.06
    POSITIVE LOGITS
    ↳
    0.07
    itivity
    0.07
     strtolower
    0.07
    시설
    0.07
     Sisters
    0.07
    смотр
    0.06
    -factor
    0.06
    _STRIP
    0.06
    ත
    0.06
    ->{_
    0.06
    Act Density 0.063%

    No Known Activations