INDEX

Explanations

generation

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

isma

-0.27

 hairs

-0.27

istency

-0.25

ÐºÐ¾Ð²Ð°

-0.25

å¹²æ¶ī

-0.25

emean

-0.25

ServerError

-0.25

NBC

-0.25

ï¸

-0.25

å¤±è´¥

-0.24

POSITIVE LOGITS

 capacity

0.38

 connections

0.38

 connection

0.37

 Connecting

0.34

è¿ŀæİ¥

0.34

 built

0.34

connections

0.33

å®¹éĩı

0.33

 connected

0.33

Connecting

0.32

Activations Density 0.102%