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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ⲛ
    0.65
    favorites
    0.63
    性和
    0.63
    वेदनशील
    0.63
    度和
    0.62
    Themes
    0.61
    heroes
    0.59
     、,
    0.57
    товые
    0.57
     wichtigen
    0.57
    POSITIVE LOGITS
     =
    0.89
    }=
    0.68
     :
    0.66
    )=
    0.66
     sehingga
    0.64
     şeklinde
    0.62
    =
    0.62
     $=
    0.62
     resulting
    0.59
     ≈
    0.57
    Act Density 0.084%

    No Known Activations