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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝗶
    0.49
     видно
    0.43
    부터
    0.41
     воды
    0.41
    bye
    0.40
    𝙞
    0.40
    ش
    0.40
    ﮯ
    0.40
    ш
    0.39
    и
    0.39
    POSITIVE LOGITS
     different
    0.52
     disparate
    0.50
     inseparable
    0.49
    つの
    0.49
     différents
    0.48
    сот
    0.48
     अपेक्षाकृत
    0.47
    迥
    0.47
     únicos
    0.46
     interdependent
    0.46
    Act Density 0.077%

    No Known Activations