INDEX

Explanations

`. Gan`, `. The`, `. James`

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

 then

-1.30

ὴν

-1.01

 Then

-0.98

 kemudian

-0.94

ienta

-0.91

 natomiast

-0.91

 changes

-0.90

any

-0.90

 ثم

-0.90

 joten

-0.90

POSITIVE LOGITS

🚑

0.86

arschu

0.82

 שה

0.80

 ales

0.78

 bereits

0.78

ताओं

0.77

映

0.77

₋

0.77

ätten

0.77

 уже

0.77

Activations Density 0.111%