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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    m
    1.01
    F
    0.98
    0.83
    ↵
    0.76
    A
    0.76
     reputation
    0.75
    d
    0.75
    minister
    0.71
    s
    0.71
    C
    0.70
    POSITIVE LOGITS
     việc
    0.99
     आल्सो
    0.89
     것입니다
    0.83
    éseket
    0.78
    átu
    0.77
     coalgebras
    0.77
     herramient
    0.75
     LPTMR
    0.75
     chuyện
    0.74
     इजी
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.