INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pas

-0.11

arm

-0.09

pos

-0.09

 underneath

-0.09

anton

-0.09

RPC

-0.09

ula

-0.08

cas

-0.08

FK

-0.08

rollo

-0.08

POSITIVE LOGITS

iesel

0.10

oba

0.09

 Merr

0.09

 Bentley

0.09

 Fres

0.08

 Morton

0.08

 Pruitt

0.08

 Wert

0.08

Alv

0.08

 Ingram

0.08

Activations Density 0.000%

No Known Activations