INDEX

Explanations

neural network layers Dense FC linear conv

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

while

-1.77

 whereas

-1.61

'])->

-1.58

 while

-1.57

 mentre

-1.55

↵

-1.49

 sedangkan

-1.40

 mientras

-1.38

↵↵↵↵↵↵

-1.37

どちら

-1.36

POSITIVE LOGITS

2.08

1.34

建議

1.31

1.26

↵↵

1.22

 Conseils

1.20

涐

1.20

boldsymbol

1.20

<bos>

1.19

 caminhada

1.18

Activations Density 0.007%