INDEX

Explanations

lo

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

ymce

-0.47

sub

-0.44

thâu

-0.40

dant

-0.40

 Conley

-0.38

BitmapFactory

-0.38

binant

-0.37

 čin

-0.37

Configurations

-0.36

arXiv

-0.35

POSITIVE LOGITS

 propOrder

0.64

pable

0.62

ThroughAttribute

0.62

vable

0.60

 attaques

0.59

GEBURTSDATUM

0.59

athe

0.59

ath

0.57

fiets

0.57

GEBURTS

0.57

Activations Density 0.005%