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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    stage
    -0.75
    module
    -0.73
    fold
    -0.69
     nutshell
    -0.69
    hedon
    -0.69
    packed
    -0.67
    essions
    -0.66
    '/
    -0.65
    pull
    -0.65
    gallery
    -0.64
    POSITIVE LOGITS
    ilon
    0.72
    onde
    0.71
     cous
    0.68
     hindsight
    0.66
     cler
    0.66
    £ı
    0.64
    ateurs
    0.64
     Fidel
    0.63
     Vlad
    0.63
     classics
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.