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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    enne
    -0.79
    ipe
    -0.76
    ingers
    -0.76
    ibble
    -0.69
    ande
    -0.66
    iber
    -0.66
    ipers
    -0.64
    ourage
    -0.63
    inging
    -0.63
    iman
    -0.63
    POSITIVE LOGITS
    minist
    0.71
    ãĤ¡
    0.69
    Saudi
    0.67
    Owner
    0.64
    +(
    0.62
     ±
    0.62
     fulfillment
    0.62
    Module
    0.60
     easing
    0.60
    caster
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.