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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    스로
    1.06
     darling
    1.00
    czne
    1.00
    inal
    1.00
     litmus
    0.99
    ين
    0.99
    伏
    0.98
    le
    0.98
    近
    0.98
    yy
    0.96
    POSITIVE LOGITS
    𝑜
    1.26
    샐
    1.25
     handelt
    1.23
     oed
    1.22
     sogenannte
    1.21
    úa
    1.20
    ,\,
    1.19
    Ǥ
    1.19
    ἥ
    1.17
    𝑅
    1.16
    Act Density 0.000%

    No Known Activations