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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     convincingly
    1.33
     Κ
    1.20
     chroma
    1.20
    К
    1.16
     numerous
    1.15
     fudge
    1.15
     clinically
    1.14
     probl
    1.12
     whak
    1.12
     sens
    1.09
    POSITIVE LOGITS
    ند
    1.51
    ני
    1.31
    ين
    1.26
    {@
    1.15
     אף
    1.10
    ńczy
    1.09
    uitse
    1.09
    ésre
    1.06
     של
    1.05
    ute
    1.04
    Act Density 0.145%

    No Known Activations