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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     smelly
    0.91
    ны
    0.89
     stabbing
    0.89
     panties
    0.88
     nerdy
    0.88
     flavon
    0.87
     humanist
    0.87
     dysfunctional
    0.87
     itchy
    0.87
     knowledgeable
    0.85
    POSITIVE LOGITS
    i
    1.10
    H
    1.03
    S
    1.00
    X
    0.98
    N
    0.97
    W
    0.96
    U
    0.91
    B
    0.91
    V
    0.89
    D
    0.88
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.