INDEX

Explanations

emit

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

emit

-1.06

 emit

-1.06

 emitting

-0.98

 emitter

-0.96

 emitted

-0.96

 emits

-0.95

emitter

-0.93

 emission

-0.86

Emit

-0.83

 Emit

-0.82

POSITIVE LOGITS

 colored

0.50

CrossRef

0.50

 coloured

0.46

 chords

0.46

Portail

0.45

subsubsection

0.45

Jax

0.45

trons

0.44

 service

0.44

 pick

0.44

Activations Density 0.112%