INDEX

Explanations

an

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 benef

-0.28

.mp

-0.27

 especÃŃfico

-0.26

ington

-0.25

SX

-0.25

DY

-0.25

DY

-0.25

èĥ

-0.24

åıĳå±ķåİĨç¨ĭ

-0.24

å»¶

-0.24

POSITIVE LOGITS

itage

0.34

 Georgian

0.27

ocaust

0.27

 Balt

0.26

ľ

0.26

agg

0.26

*i

0.25

zig

0.25

emann

0.25

Warn

0.24

Activations Density 0.001%