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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     alguma
    1.20
    貅
    1.16
     deng
    1.07
     Wszyst
    1.07
     Encoder
    1.06
     Sama
    1.05
     softmax
    1.04
    }$&
    1.02
     Invisible
    1.02
     tepi
    1.01
    POSITIVE LOGITS
    ductory
    1.10
    ان
    1.10
    лень
    1.00
    稚
    0.98
    \{
    0.97
    リーム
    0.97
    jected
    0.96
    тык
    0.95
    fony
    0.95
     batters
    0.93
    Act Density 0.000%

    No Known Activations