INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ry

-0.11

aland

-0.10

 Boyle

-0.10

TM

-0.09

inand

-0.09

Ã¤tz

-0.09

 Controlled

-0.09

 Passed

-0.08

urer

-0.08

@gmail

-0.08

POSITIVE LOGITS

 hitch

0.11

ward

0.10

 Lies

0.10

 shaky

0.09

 Fair

0.09

_nh

0.09

 errone

0.08

 stubborn

0.08

 charm

0.08

 questionable

0.08

Activations Density 0.000%

No Known Activations