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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rers
    -0.64
    istine
    -0.61
    ãĤ´
    -0.60
    ocus
    -0.60
    odder
    -0.60
    rying
    -0.59
    itte
    -0.59
    awed
    -0.57
     powers
    -0.57
    states
    -0.57
    POSITIVE LOGITS
     Lime
    0.71
    hran
    0.70
     MF
    0.69
     FB
    0.68
     Seym
    0.67
    eus
    0.67
    BAT
    0.66
    anian
    0.65
     Plex
    0.64
     JO
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.