INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tasting

-0.10

EIF

-0.09

 kunt

-0.09

 tamp

-0.09

beans

-0.09

 appeals

-0.09

 Harmon

-0.09

GIR

-0.09

CY

-0.09

Gir

-0.08

POSITIVE LOGITS

 flare

0.12

roz

0.11

 dressed

0.09

flare

0.09

nat

0.08

ega

0.08

PREC

0.08

peg

0.08

Lv

0.08

eln

0.08

Activations Density 0.000%

No Known Activations