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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     booth
    -0.29
    éĤ®
    -0.27
    ä¾Ľç»Ļ侧
    -0.26
    IMENT
    -0.26
    ãĥªãĥ³
    -0.26
    éĢģåİ»
    -0.25
    ication
    -0.25
    ilege
    -0.24
    enumerator
    -0.24
     hamburger
    -0.24
    POSITIVE LOGITS
    attended
    0.28
    èĢķ
    0.28
    æľīä¸Ģ次
    0.26
     altern
    0.25
    ato
    0.24
    (aux
    0.24
    jin
    0.24
     hypoth
    0.24
     alternate
    0.24
    ouv
    0.23
    Act Density 0.006%

    No Known Activations

    This feature has no known activations.