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

peg

-0.09

 Hayward

-0.09

 Pied

-0.09

akis

-0.09

 trot

-0.09

 Herc

-0.08

erras

-0.08

 entr

-0.08

zk

-0.08

mk

-0.08

POSITIVE LOGITS

ader

0.10

essler

0.10

 gamm

0.10

SAME

0.09

 discreet

0.09

 stad

0.09

 motivation

0.09

avail

0.09

 adel

0.09

ocup

0.09

Activations Density 0.000%

No Known Activations