INDEX

Explanations

AS

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

as

-0.80

all

-0.79

AS

-0.79

SHE

-0.59

like

-0.57

we

-0.57

um

-0.55

she

-0.51

aker

-0.50

POSITIVE LOGITS

 يتيمه

1.05

 '\\;'

0.98

Билгалдахарш

0.96

WithIOException

0.96

 Signalez

0.91

 gynhyrchwyd

0.90

Cyfeiriadau

0.89

évaluateur

0.88

 Мексичка

0.85

NUMX

0.83

Activations Density 0.040%