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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    åı¯æĥ³
    -0.28
    åħħåĪĨåıijæĮ¥
    -0.25
    éļ¾è¿ĩ
    -0.24
    æIJª
    -0.24
     iface
    -0.23
     happiest
    -0.23
    幸ç¦ı
    -0.23
     Notebook
    -0.23
    iface
    -0.23
    accion
    -0.23
    POSITIVE LOGITS
    亥
    0.27
    lei
    0.26
    romatic
    0.25
    HU
    0.25
    FU
    0.25
    饮
    0.25
    лей
    0.24
    JUST
    0.24
    inance
    0.24
     Hu
    0.24
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.