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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    :b
    -0.08
    �
    -0.08
    无
    -0.07
    babel
    -0.07
    ఆ
    -0.07
     tamb
    -0.07
     mail
    -0.07
     swamp
    -0.07
    写了
    -0.07
     NYT
    -0.07
    POSITIVE LOGITS
     receptor
    0.10
    ket
    0.08
    EntityType
    0.08
     Rece
    0.07
    其实就是
    0.07
    auge
    0.07
    .getCount
    0.07
    从业人员
    0.07
    reeting
    0.07
    因为他
    0.07
    Act Density 0.010%

    No Known Activations