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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.09
    3:0.09
    4:0.09
    5:0.07
    6:0.08
    7:0.06
    8:0.07
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
     theorem
    -1.61
     joke
    -1.45
     MacArthur
    -1.45
     Ludwig
    -1.42
     Bloom
    -1.42
     Stall
    -1.41
    qq
    -1.38
     Sherman
    -1.35
     MSM
    -1.35
     quote
    -1.34
    POSITIVE LOGITS
    conservancy
    2.04
    ADRA
    1.83
    uckland
    1.80
    tera
    1.79
    earch
    1.78
    abwe
    1.78
    mbuds
    1.78
     showc
    1.78
     withd
    1.72
     confir
    1.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.