INDEX

Explanations

special formatting or naming conventions in programming, particularly in function and variable names

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

/goto

-0.08

 traps

-0.07

itou

-0.07

çİ°åľº

-0.07

 trap

-0.07

trap

-0.07

olini

-0.07

erea

-0.07

USIC

-0.06

 Trap

-0.06

POSITIVE LOGITS

 stroke

0.25

roke

0.25

 strike

0.24

 Stroke

0.23

 Strike

0.23

 strokes

0.23

 strikes

0.23

stroke

0.23

Stroke

0.22

 struck

0.21

Activations Density 0.008%