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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    itable
    -0.81
    ÃŃs
    -0.77
    rete
    -0.75
    mson
    -0.71
    bley
    -0.68
    ova
    -0.68
    atures
    -0.67
    riers
    -0.66
    iton
    -0.66
    uzz
    -0.66
    POSITIVE LOGITS
     pronunciation
    0.70
     crib
    0.68
    Interstitial
    0.67
     baptism
    0.66
     sax
    0.65
     spelling
    0.65
     resemblance
    0.65
    alam
    0.64
     toe
    0.63
     partying
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.