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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     I
    1.55
     B
    1.55
     C
    1.54
     [
    1.54
     G
    1.45
     R
    1.40
     M
    1.39
     E
    1.38
     P
    1.35
     c
    1.33
    POSITIVE LOGITS
     намного
    2.01
    fromParams
    1.99
    㣙
    1.90
    Beverungen
    1.85
    㼛
    1.85
    㜖
    1.83
    敺
    1.83
     emocion
    1.82
    FURNIZOR
    1.81
    嬠
    1.80
    Act Density 0.171%

    No Known Activations