INDEX

Explanations

data related to mathematical symbols and parameters in equations

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fib

-0.06

regexp

-0.06

rength

-0.06

fib

-0.06

ĶĦ

-0.05

apest

-0.05

 brushing

-0.05

pus

-0.05

strength

-0.05

 tactile

-0.05

POSITIVE LOGITS

 steam

0.13

 Steam

0.12

 stall

0.11

Steam

0.11

 Stall

0.10

 Heat

0.10

 Boiler

0.10

 Outlet

0.10

steam

0.09

 heat

0.09

Activations Density 0.002%