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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     badges
    -0.72
     credentials
    -0.69
     pods
    -0.67
     beds
    -0.66
     certificates
    -0.66
    gpu
    -0.66
     buckets
    -0.65
     paths
    -0.65
    acons
    -0.64
    coming
    -0.64
    POSITIVE LOGITS
    alian
    0.89
    orno
    0.84
    theless
    0.76
    roman
    0.72
     Bake
    0.68
    xual
    0.68
     Confeder
    0.66
    aid
    0.66
    ptin
    0.66
    air
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.