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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    umenthal
    -0.70
     brewers
    -0.69
    arnaev
    -0.67
     killers
    -0.66
     pens
    -0.66
     strand
    -0.65
     Strikes
    -0.62
     ECB
    -0.62
    uve
    -0.61
    strip
    -0.61
    POSITIVE LOGITS
    estamp
    0.76
    hip
    0.72
    aby
    0.72
    ias
    0.68
    ectomy
    0.66
    emn
    0.65
    ios
    0.65
    irm
    0.65
    oor
    0.64
    Zip
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.