INDEX

Explanations

texts related to crimes, particularly those motivated by hate or aggression

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

burgh

-0.08

å¥Ķ

-0.07

Ä±lÄ±ÅŁ

-0.07

ampo

-0.07

nett

-0.07

yre

-0.07

crets

-0.07

olec

-0.06

rrha

-0.06

åīĽ

-0.06

POSITIVE LOGITS

asco

0.07

udy

0.06

 Stocks

0.06

 deferred

0.06

defer

0.06

ç¿¼

0.06

Ã½Å¡

0.06

_ptr

0.05

XP

0.05

Activations Density 0.001%