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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     již
    1.59
    하였습니다
    1.52
     endast
    1.50
     אשר
    1.47
     매우
    1.45
    maktadır
    1.45
     etmektedir
    1.45
     것입니다
    1.45
     zeer
    1.45
     사용하여
    1.40
    POSITIVE LOGITS
     kinda
    1.76
     weird
    1.72
     kind
    1.60
     guys
    1.52
    weird
    1.40
     yeah
    1.37
     totally
    1.34
     stuff
    1.33
     sort
    1.26
    Yeah
    1.25
    Act Density 0.904%

    No Known Activations