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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Reviewed
    -0.69
    chester
    -0.65
     quiz
    -0.65
     Pixie
    -0.64
     SCHOOL
    -0.63
    azine
    -0.60
    lier
    -0.58
     KY
    -0.58
     Wembley
    -0.58
     darts
    -0.58
    POSITIVE LOGITS
    irez
    0.79
     recip
    0.75
    EStream
    0.73
    idas
    0.73
    withstanding
    0.72
    aucas
    0.72
    orsi
    0.72
    ertodd
    0.69
     Cosponsors
    0.68
     Prelude
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.