INDEX

Explanations

references to geographic locations or administrative divisions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hait

-0.08

åĿĬ

-0.07

ghi

-0.07

 kaps

-0.07

á»©ng

-0.07

pollo

-0.07

 Giá»Ľi

-0.07

berger

-0.07

angl

-0.06

ÙĩÙĨÚ¯

-0.06

POSITIVE LOGITS

Sax

0.17

 Lower

0.16

 Brand

0.15

Bad

0.14

Rh

0.13

 Sach

0.13

Th

0.13

Lower

0.12

Brand

0.12

Sa

0.11

Activations Density 0.014%