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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mél
    0.57
     conceivably
    0.56
     aventure
    0.54
     legitimately
    0.53
     trich
    0.53
     uniquement
    0.52
     yǒu
    0.52
     produkter
    0.51
     underpin
    0.50
     repentance
    0.49
    POSITIVE LOGITS
    ه
    0.54
    Reset
    0.53
     #{@
    0.53
     Reset
    0.50
    人人
    0.50
    راک
    0.50
    本
    0.50
     Encoding
    0.49
    ！
    0.48
    ﺮ
    0.48
    Act Density 0.000%

    No Known Activations