INDEX

Explanations

so followed by adjective or adverb

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

is

-1.82

and

-1.66

still

-1.55

趼

-1.49

Ꮉ

-1.46



-1.45

 campeón

-1.42

BUT

-1.41

who

-1.41

ed

-1.40

POSITIVE LOGITS

 think

1.38

̃o

1.38

 around

1.27

 зару

1.27

 zwłaszcza

1.27

 például

1.20

wnętr

1.18

[]:

1.17

mathrm

1.17

istä

1.16

Activations Density 0.017%