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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Assets
    -0.76
     Tycoon
    -0.73
     Educational
    -0.69
     Colleges
    -0.68
     Intent
    -0.64
    ropolitan
    -0.64
    erella
    -0.64
    CLASS
    -0.63
     Ratings
    -0.63
    ee
    -0.63
    POSITIVE LOGITS
    cussion
    0.83
    stead
    0.74
     desper
    0.70
    cow
    0.65
     evils
    0.65
     Jinn
    0.61
     Boone
    0.60
     BALL
    0.60
    strength
    0.60
    choes
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.