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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     장
    0.91
     eclectic
    0.80
     khủng
    0.79
     비슷한
    0.78
     강화
    0.76
     baroque
    0.76
     추천
    0.75
     gourmet
    0.75
     bespoke
    0.75
     예술
    0.74
    POSITIVE LOGITS
     decrement
    1.22
     iterates
    1.20
     iterating
    1.11
     iterate
    1.10
    Iteration
    1.08
     iteration
    1.07
    Decrement
    1.06
     increment
    1.04
     leftmost
    1.04
     consecut
    1.03
    Act Density 2.571%

    No Known Activations