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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    under
    -0.08
     Version
    -0.08
    front
    -0.07
    ade
    -0.07
    Better
    -0.07
    ram
    -0.07
    LEN
    -0.07
    =@
    -0.07
    其所
    -0.07
    是一家
    -0.07
    POSITIVE LOGITS
     zwł
    0.07
    ϳ
    0.07
    Ӈ
    0.07
    .nextToken
    0.07
    意味
    0.07
     aw
    0.06
     licked
    0.06
    即将到来
    0.06
    蜂蜜
    0.06
     widać
    0.06
    Act Density 0.001%

    No Known Activations