INDEX

Explanations

scientific/technical

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

æµ®

-0.32

quo

-0.28

 errno

-0.28

.PerformLayout

-0.28

lich

-0.26

 fluid

-0.26

 Wildcats

-0.25

å¯¹èĩªå·±

-0.25

assen

-0.25

.elem

-0.25

POSITIVE LOGITS

pray

0.28

 Invisible

0.28

hap

0.27

_INST

0.26

ificador

0.26

ÑģÐµÑĤ

0.26

owie

0.25

ÐµÑĢÑĭ

0.25

van

0.25

çĽı

0.24

Activations Density 0.885%