INDEX

Explanations

SR flipflop, code variables, MLS numbers

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

朏

-2.31

 shrill

-2.22



-2.17

쌩

-2.16

 аккура

-2.13

 comienzos

-2.13

᯾

-2.11

ciona

-2.11

︲

-2.09

 Itália

-2.08

POSITIVE LOGITS

3.03

2.53

ться

2.34

ization

2.25

 possa

2.23

〬

2.20

 luminoso

2.09

一旁的

2.08

彼の

2.05

 kwamba

2.05

Activations Density 0.012%