INDEX

Explanations

references to figures or diagrams

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 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

 myſelf

-0.72

ContentAsync

-0.65

 вроде

-0.64

 EconPapers

-0.63

 themſelves

-0.60

Còn

-0.60

xffffffff

-0.60

vernight

-0.59

cunt

-0.59

 itſelf

-0.59

POSITIVE LOGITS

Fig

3.08

Fig

3.05

fig

2.94

fig

2.77

FIG

2.52

FIG

2.52

 Figs

2.50

 Figure

2.41

Figure

2.39

Figs

2.30

Activations Density 4.036%