INDEX

Explanations

words starting with ef or eph

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Вікі

-0.87

Pik

-0.82

 embeddings

-0.81

 آم

-0.78

 Hearings

-0.77

Subtotal

-0.77

ssf

-0.76

 Speeches

-0.75

ourites

-0.71

 Recre

-0.71

POSITIVE LOGITS

EF

1.12

ef

1.02

Ef

0.90

EF

0.81

DEF

0.73

Ef

0.72

ef

0.71

Eff

0.70

 later

0.70

kać

0.70

Activations Density 0.031%