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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    enegger
    -1.30
    urers
    -0.96
    thouse
    -0.94
     Gutenberg
    -0.93
    ãĤ©
    -0.90
    ebook
    -0.89
    tek
    -0.85
    displayText
    -0.83
    advertising
    -0.83
    urer
    -0.80
    POSITIVE LOGITS
     sympath
    0.73
     consolation
    0.70
     subordinate
    0.66
     reciproc
    0.65
     reflex
    0.64
     tal
    0.64
     metre
    0.63
     snatched
    0.63
     reversed
    0.62
     recognised
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.