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

çŃ¾çº¦

-0.29

 offering

-0.28

èĥª

-0.27

 Scot

-0.27

 trailing

-0.27

app

-0.25

lator

-0.24

 leading

-0.24

 oriented

-0.24

ts

-0.24

POSITIVE LOGITS

APON

0.28

 healthier

0.27

 investigation

0.26

 selves

0.25

 TODAY

0.25

 tougher

0.25

èĥĨ

0.25

âĺİ

0.24

-fontawesome

0.24

æĽ´å¥½

0.24

Activations Density 0.011%

No Known Activations

This feature has no known activations.