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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Tipp
    1.91
    etr
    1.83
    デイ
    1.80
    イ
    1.77
    舅
    1.77
     lược
    1.75
     TRO
    1.72
     chronology
    1.71
     hội
    1.70
    ｖ
    1.70
    POSITIVE LOGITS
    7
    1.99
    3
    1.93
    6
    1.86
    5
    1.84
    4
    1.81
    8
    1.65
    2
    1.61
    1
    1.50
    binicons
    1.45
    9
    1.43
    Act Density 0.538%

    No Known Activations