INDEX

Explanations

No Explanations Found

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

indy

-0.26

 undecided

-0.25

 above

-0.25

above

-0.25

 UNUSED

-0.24

åħįç¨İ

-0.24

noinspection

-0.24

[__

-0.23

æĹłæķĮ

-0.23

ç¦§

-0.23

POSITIVE LOGITS

sic

0.26

square

0.25

Ð¸ÑĤÑĮ

0.24

atile

0.24

sil

0.24

 medi

0.23

Faculty

0.23

ä¼´

0.23

inha

0.23

itol

0.23

Activations Density 0.015%

No Known Activations

This feature has no known activations.