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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ogyn
    -0.77
    advertising
    -0.76
    ypes
    -0.73
     asses
    -0.73
    humans
    -0.70
     "$:/
    -0.69
    omsky
    -0.69
    gex
    -0.68
    clinical
    -0.66
    ormonal
    -0.66
    POSITIVE LOGITS
     Daniels
    0.75
    OOL
    0.74
     Kun
    0.73
     Knot
    0.70
     KC
    0.67
     Rudolph
    0.66
    ller
    0.66
    geist
    0.66
     Revelation
    0.65
     Ka
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.