INDEX

Explanations

names followed by numbers or context

The neuron responds strongly to tokens that form place names (geographical location names).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

1.59

 नामक

1.57

1.54

’

1.52

 adlı

1.52

1.48

and

1.45

 மற்றும்

1.45

1.36

1.35

POSITIVE LOGITS

UIntValue

1.17

pieceSelection

1.15

 nontrivial

1.15

VerFile

1.10

ፈለ

1.05

timevals

1.04

 childlike

1.04

elevationMap

1.03

parvec

1.03

ጠቀ

1.03

Activations Density 0.009%