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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    POST
    -0.78
    nery
    -0.75
    malink
    -0.73
    atically
    -0.72
    form
    -0.67
    ooter
    -0.66
     Quit
    -0.66
    served
    -0.66
    self
    -0.65
    sel
    -0.64
    POSITIVE LOGITS
     exha
    0.68
     veter
    0.68
     pend
    0.66
     earthquakes
    0.65
     gobl
    0.65
     weighted
    0.65
     incumb
    0.64
     Era
    0.62
     misunder
    0.61
     intrig
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.