INDEX

Explanations

words followed by that

demonstrative pronouns

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

 acest

1.18

 aquela

1.16

那個

1.15

 această

1.11

 этого

1.10

 aquele

1.09

 tersebut

1.08

 그걸

1.04

この

1.02

那个

1.02

POSITIVE LOGITS

th

0.53

thi

0.50

 thisStudent

0.43

⃛

0.41

 thay

0.40

 Thos

0.39

tha

0.38

كيت

0.38

úcar

0.37

িয়াছি

0.37

Activations Density 0.143%