INDEX

Explanations

header

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

og

-0.26

_WINDOW

-0.25

_MPI

-0.25

 gest

-0.25

 tilted

-0.24

 eing

-0.24

çĪµå£«

-0.24

æ½´

-0.24

 darauf

-0.24

mp

-0.23

POSITIVE LOGITS

çº¿è·¯

0.30

çģ«

0.28

rength

0.27

æľīåħ³éĥ¨éĹ¨

0.25

æ»ĳ

0.25

åı°

0.25

 scape

0.24

ivated

0.24

(dc

0.24

 percentage

0.24

Activations Density 0.093%