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

Negative Logits

complexContent

-0.89

 <=",

-0.82

 jspb

-0.82

DebuggerNonUser

-0.81

новниш

-0.77

Rüyada

-0.77

RTEE

-0.72

Brainz

-0.72

__*/

-0.71

$_['

-0.71

POSITIVE LOGITS

 dramatically

0.40

 langt

0.40

jen

0.38

textrm

0.37

gi

0.37

ádza

0.36

sch

0.36

得

0.36

 fils

0.35

vient

0.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.