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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ocard
    -0.78
    vironment
    -0.72
    uana
    -0.71
    halla
    -0.70
     Driver
    -0.70
    inki
    -0.70
     citiz
    -0.69
    ça
    -0.68
    cohol
    -0.67
    ournal
    -0.66
    POSITIVE LOGITS
     Kissinger
    0.74
     bruising
    0.73
    interstitial
    0.66
     Cosponsors
    0.66
     bombshell
    0.66
     peg
    0.65
     shattering
    0.65
    daq
    0.64
    tests
    0.63
     chuck
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.