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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    eker
    -0.66
     fertil
    -0.66
    atum
    -0.64
     package
    -0.63
     load
    -0.62
     guise
    -0.61
    ieves
    -0.60
     squeeze
    -0.59
     packages
    -0.58
     drift
    -0.57
    POSITIVE LOGITS
    boxing
    0.74
     Bers
    0.71
     Saber
    0.69
    erb
    0.68
    burg
    0.68
    ij士
    0.67
    aml
    0.65
    icip
    0.65
    lehem
    0.65
     Browne
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.