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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    uilder
    -0.17
    Inst
    -0.16
    inst
    -0.16
     inst
    -0.15
    ÅĦst
    -0.15
    uth
    -0.15
    epar
    -0.15
    ãĥ¼ãĥIJ
    -0.15
     bre
    -0.14
     Inst
    -0.14
    POSITIVE LOGITS
    /frontend
    0.16
     cig
    0.14
    shan
    0.14
    éª
    0.14
    enment
    0.14
    ελ
    0.14
     NAN
    0.14
    hoo
    0.14
    iš
    0.14
    Ý
    0.14
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.