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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Bentley
    -0.75
     buckle
    -0.71
     finite
    -0.70
     auto
    -0.64
     clot
    -0.63
     grasp
    -0.62
     const
    -0.61
     grad
    -0.61
    ctor
    -0.60
     integer
    -0.60
    POSITIVE LOGITS
    edom
    0.87
     Gork
    0.77
    ylum
    0.77
    lins
    0.77
    irth
    0.75
    iment
    0.70
    alsa
    0.69
    inical
    0.68
    terness
    0.67
    risome
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.