INDEX

Explanations

names and terms related to philosophical figures and concepts

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

ÎºÏĦÎ®

-0.08

snap

-0.08

sans

-0.07

ÏĩÎµÎ´ÏĮÎ½

-0.07

udem

-0.07

sak

-0.07

 Eudicots

-0.07

 MessageBoxButton

-0.07

san

-0.07

akens

-0.07

POSITIVE LOGITS

stein

0.25

ste

0.14

 Stein

0.13

tein

0.13

STE

0.13

ste

0.13

enstein

0.12

_ste

0.12

 steering

0.12

este

0.12

Activations Density 0.004%