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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Instruments
    -0.80
    lihood
    -0.79
     Tanz
    -0.75
    itched
    -0.74
    obar
    -0.70
    coord
    -0.68
    ersive
    -0.66
     Laz
    -0.66
    iris
    -0.65
    stead
    -0.65
    POSITIVE LOGITS
     certs
    0.75
    oute
    0.73
    icans
    0.73
     checkout
    0.73
     scout
    0.72
     disg
    0.67
     mathemat
    0.66
    ught
    0.65
     caval
    0.63
    cer
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.