INDEX

Explanations

technical, code, morphometrics

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

 Verified

-0.28

_verified

-0.27

Verified

-0.26

åĽŀèĲ½

-0.26

ç¡®è¯Ĭ

-0.26

ÑģÐ»

-0.26

umper

-0.26

-pill

-0.25

çº¤

-0.25

éľ²åĩº

-0.25

POSITIVE LOGITS

awl

0.31

ChangeEvent

0.29

Ã»t

0.27

gyr

0.25

é¤Ĭ

0.25

åĪ¹

0.24

åħ»

0.24

 offensive

0.24

 entertain

0.24

(core

0.24

Activations Density 0.005%