INDEX

Explanations

psychology

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

met

-0.29

Met

-0.28

.chunk

-0.27

åħ±

-0.27

é¹ľ

-0.25

met

-0.25

Met

-0.24

 managed

-0.24

globals

-0.24

 chunk

-0.23

POSITIVE LOGITS

å¿ĥçĲĨ

0.74

 psychological

0.67

 psychology

0.63

 Psychological

0.63

psych

0.60

å¿ĥçĲĨåŃ¦

0.60

çļĦå¿ĥçĲĨ

0.59

 psych

0.57

Psych

0.56

 psychologically

0.56

Activations Density 0.917%