INDEX

Explanations

[word] followed by [specifier]

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-1.45

useState

-1.39

 Unve

-1.37

 nhựa

-1.35

 impulsar

-1.34

뤄

-1.34

 poté

-1.33

"));

-1.32

who

-1.31

。」

-1.30

POSITIVE LOGITS

on

1.66

 usually

1.41

 this

1.40

for

1.40

one

1.38

 even

1.38

 that

1.35

 often

1.35

なども

1.34

 sometimes

1.28

Activations Density 0.117%