INDEX

Explanations

sentence start

periods and following words

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 secondly

0.53

Secondly

0.52

 এছাড়াও

0.49

[...]

0.48

 그다음에

0.47

Additionally

0.47

其次

0.46

nostic

0.46

 그러면

0.46

 дальше

0.44

POSITIVE LOGITS

៕

1.45

<eos>

1.39

↵↵↵↵↵↵↵↵↵↵↵

1.00

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.98

↵↵↵↵↵↵↵↵↵

0.95

↵↵↵↵↵↵↵↵↵↵↵↵↵

0.93

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.93

↵↵↵↵↵↵↵

0.91

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.91

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.91

Activations Density 0.386%