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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     advance
    -0.64
     stim
    -0.64
    Discuss
    -0.63
     Slay
    -0.62
     DRM
    -0.62
     ambush
    -0.61
     Band
    -0.61
     Kart
    -0.60
     Baron
    -0.60
     racket
    -0.59
    POSITIVE LOGITS
    estate
    0.81
    urized
    0.78
    wu
    0.72
    ached
    0.72
    sic
    0.70
    resa
    0.69
    olia
    0.69
    icut
    0.68
     Doe
    0.67
    hus
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.