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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    re
    1.00
    ates
    0.99
    tk
    0.96
    ate
    0.95
    ma
    0.95
    centric
    0.94
    tl
    0.92
    ci
    0.90
    d
    0.89
    ominator
    0.88
    POSITIVE LOGITS
    🙏🙏
    1.17
     scams
    1.11
     tensors
    1.10
     MSG
    1.07
     jogging
    1.06
     JsonConvert
    1.06
     Iber
    1.05
     Gucci
    1.04
     Spartans
    1.04
    ถุนายน
    1.03
    Act Density 0.000%

    No Known Activations