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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    что
    1.27
    که
    0.99
     reis
    0.98
     temper
    0.95
     scorn
    0.95
     als
    0.95
     kind
    0.94
    >;
    0.93
     Marlon
    0.93
    داد
    0.90
    POSITIVE LOGITS
     thậm
    1.10
    containsKey
    1.10
    तल
    1.09
     آئینے
    1.03
     covariance
    1.03
    ós
    1.00
     முற
    1.00
    шення
    0.99
     באי
    0.99
     هیڅ
    0.99
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.