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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     propOrder
    -0.97
    tagHelperRunner
    -0.93
     Italijani
    -0.90
     AssemblyCompany
    -0.88
    OGND
    -0.84
    Personendaten
    -0.83
    TagMode
    -0.83
    ValueStyle
    -0.81
     nahilalakip
    -0.81
     كومونز
    -0.77
    POSITIVE LOGITS
    '
    0.50
     way
    0.45
     
    0.44
    ’
    0.43
    ...
    0.40
    .
    0.40
    요
    0.40
     Dane
    0.40
     suci
    0.40
    ↵↵
    0.39
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.