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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cap
    -0.07
    aders
    -0.07
     Pav
    -0.07
    anti
    -0.06
     killed
    -0.06
    ones
    -0.06
     Gson
    -0.06
    etsy
    -0.06
     Human
    -0.06
    iterated
    -0.06
    POSITIVE LOGITS
     appointments
    0.07
     arom
    0.07
    撷
    0.07
     hydr
    0.07
     própria
    0.06
    Parm
    0.06
    用微信
    0.06
    센터
    0.06
     vừa
    0.06
    在我的
    0.06
    Act Density 0.008%

    No Known Activations