INDEX

Explanations

key functional words pertaining to claims, strategies, and discussions related to policies or issues

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

:UIAlert

-0.08

ndon

-0.07

igsaw

-0.06

iens

-0.06

ugi

-0.06

ï»¿#

-0.06

seys

-0.06

iefs

-0.06

Ãªtes

-0.06

zioni

-0.06

POSITIVE LOGITS

 which

0.08

 Which

0.08

Which

0.07

which

0.07

 mÃł

0.07

 WHICH

0.07

ement

0.06

cui

0.06

few

0.06

.which

0.06

Activations Density 0.023%