INDEX

Explanations

words and phrases that express personal connections or relationships

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ISTA

-0.08

ufen

-0.07

erde

-0.07

Ø§ÙĦØ§

-0.07

olest

-0.07

éĢĢ

-0.07

Ð¾Ð»Ð¾Ð´

-0.07

ãĤĵãģª

-0.07

deen

-0.07

ÂŃi

-0.07

POSITIVE LOGITS

 frequent

0.08

 part

0.07

 distant

0.06

Ð¹Ð½

0.06

 admir

0.06

requent

0.06

ops

0.06

 instrumental

0.06

 among

0.05

 sert

0.05

Activations Density 0.018%