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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     summons
    -0.80
    icts
    -0.69
     rall
    -0.67
     upgrades
    -0.66
     fortun
    -0.65
    iary
    -0.62
     withd
    -0.62
     deficient
    -0.62
     conclud
    -0.62
    iar
    -0.61
    POSITIVE LOGITS
    edia
    0.80
    pocket
    0.74
     aside
    0.69
     Mellon
    0.68
     Qué
    0.67
    ampa
    0.65
     Wik
    0.64
     Chung
    0.64
     Rochester
    0.64
     Pistol
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.