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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    MODE
    -1.03
    SourceFile
    -0.87
    POS
    -0.82
    ratulations
    -0.81
    mask
    -0.77
    Champ
    -0.77
    potion
    -0.76
    Pac
    -0.75
    sworth
    -0.73
    Ĥª
    -0.73
    POSITIVE LOGITS
     afar
    1.01
     behalf
    0.93
    coming
    0.89
     Capitol
    0.84
    shore
    0.83
     top
    0.80
    eday
    0.79
    site
    0.75
     whence
    0.73
     conception
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.