INDEX

Explanations

women

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



-0.89

ngrx

-0.79

 "..\..\

-0.78

 againſt

-0.77

enumi

-0.77

fromnode

-0.76

 "..\..\..\

-0.76

principalTable

-0.76

 pleaſure

-0.75

Hochspringen

-0.74

POSITIVE LOGITS

Ri

0.42

II

0.41

alei

0.40

LC

0.39

Tri

0.38

 Parigi

0.38

Le

0.38

 coming

0.37

IL

0.36

Activations Density 0.011%