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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     advisory
    1.13
     strength
    1.11
     believers
    1.11
     cavalry
    1.08
     rookies
    1.08
     addiction
    1.07
     uprising
    1.06
     gathering
    1.05
     hypothesis
    1.04
     growing
    1.03
    POSITIVE LOGITS
     наме
    1.02
    s
    0.91
    ongo
    0.91
    nez
    0.91
    lii
    0.89
    loj
    0.87
    nij
    0.85
     obie
    0.85
    nest
    0.82
    obra
    0.82
    Act Density 0.000%

    No Known Activations