INDEX

Explanations

phrases that express uncertainty or speculation

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

oader

-0.06

annon

-0.06

HRESULT

-0.06

Ãºp

-0.06

Ã§os

-0.05

ervas

-0.05

encil

-0.05

 Fusion

-0.05

.Encode

-0.05

 orient

-0.05

POSITIVE LOGITS

 apparently

0.24

 turns

0.23

 Apparently

0.23

Apparently

0.22

 seems

0.21

 Turns

0.21

 Seems

0.19

 seem

0.18

 appears

0.17

Looks

0.17

Activations Density 0.072%