INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

entuan

1.64

াস্থ্য

1.59

thorace

1.57

cenik

1.55

 massima

1.53

 হাসপাত

1.52

クエスト

1.52

বর্তন

1.52

 défini

1.48

 kinases

1.47

POSITIVE LOGITS

Bar

1.10

idot

1.05

Sh

0.97

ალ

0.97

Yes

0.96

ir

0.94

Sin

0.90

ן

0.90

 Blot

0.90

 Cotton

0.90

Activations Density 0.000%

No Known Activations