INDEX

Explanations

cal

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

ensa

-0.30

åĳ¨è½¬

-0.27

rink

-0.27

äº¡

-0.27

 Frag

-0.27

immune

-0.26

NAN

-0.25

æŃ¦æŀĹ

-0.25

/ns

-0.25

liner

-0.24

POSITIVE LOGITS

cal

1.14

-cal

0.98

Cal

0.97

cal

0.96

Cal

0.96

_cal

0.88

(cal

0.85

-Cal

0.84

cal

0.83

.cal

0.82

Activations Density 0.884%