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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     IPM
    -0.68
    ancies
    -0.68
    aves
    -0.65
    ibilities
    -0.65
     ank
    -0.65
    ault
    -0.63
    ighth
    -0.63
     interoper
    -0.63
    tons
    -0.62
    estern
    -0.61
    POSITIVE LOGITS
    ãĤ¡
    0.77
    ãĥ¼ãĥĨãĤ£
    0.75
    alan
    0.74
    uton
    0.72
    govtrack
    0.70
     Flavoring
    0.68
    ratch
    0.65
    pling
    0.65
     Day
    0.65
    76561
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.