INDEX

Explanations

No Explanations Found

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

å°ļ

-0.26

åĪĩ

-0.26

enti

-0.26

core

-0.25

çİĽ

-0.25

çİ¯çĲĥ

-0.25

sty

-0.25

ophile

-0.24

æĬ¹

-0.24

å¤§åĪĩ

-0.24

POSITIVE LOGITS

abled

0.30

 arms

0.26

åĸĻ

0.26

ifty

0.24

-labelled

0.24

ilit

0.24

onnÃ©

0.23

ylan

0.23

Licensed

0.23

RANDOM

0.23

Activations Density 0.885%

No Known Activations

This feature has no known activations.