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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     worldRank
    1.08
     myopia
    1.04
     stoichiometric
    0.99
    usetts
    0.99
     merkle
    0.97
     clearest
    0.95
     ubiquitous
    0.94
     жена
    0.93
    ௫
    0.93
     foil
    0.92
    POSITIVE LOGITS
    ות
    1.01
    સ
    1.00
    а
    0.97
    𝐚
    0.94
    이
    0.89
     Тогда
    0.89
    म
    0.87
    ো
    0.86
    𝐞
    0.84
    ो
    0.83
    Act Density 0.006%

    No Known Activations