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
    1:0.08
    2:0.07
    3:0.07
    4:0.08
    5:0.09
    6:0.08
    7:0.09
    8:0.07
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    \)
    -2.91
    』
    -2.79
     Resistance
    -2.73
     Manson
    -2.67
     Harmon
    -2.66
    ァ
    -2.65
    『
    -2.62
    \">
    -2.52
     Coulter
    -2.48
    %"
    -2.40
    POSITIVE LOGITS
    window
    2.98
    Cmd
    2.91
    rawdownloadcloneembedreportprint
    2.78
     cmd
    2.66
    rontal
    2.63
     defic
    2.58
    bytes
    2.47
     commanders
    2.46
    Detailed
    2.45
    voy
    2.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.