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

 spar

-0.13

ACS

-0.09

Arn

-0.09

ouis

-0.09

eters

-0.09

 Charl

-0.09

 Charity

-0.08

 Multi

-0.08

 Arnold

-0.08

jie

-0.08

POSITIVE LOGITS

 hors

0.11

gi

0.10

 stub

0.09

-equ

0.09

adan

0.09

pell

0.09

 Glad

0.09

.equ

0.09

 fruition

0.09

nat

0.09

Activations Density 0.000%

No Known Activations