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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    loo
    -0.78
    population
    -0.73
    patch
    -0.72
    Population
    -0.71
    aukee
    -0.68
     ripe
    -0.68
    clips
    -0.67
    Roberts
    -0.67
    maxwell
    -0.63
    cffff
    -0.63
    POSITIVE LOGITS
     attempt
    0.68
    (_
    0.66
     Annotations
    0.65
     Lans
    0.65
     mages
    0.64
    ental
    0.64
    eds
    0.63
     Aim
    0.62
     Mages
    0.61
     Hua
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.