INDEX

Explanations

expressions of positivity related to experiences or situations

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

emoc

-0.07

amaz

-0.07

iÄħ

-0.07

umpt

-0.07

bef

-0.07

áº¥u

-0.07

','','

-0.07

chief

-0.06

gesch

-0.06

nite

-0.06

POSITIVE LOGITS

stell

0.09

ÅĻÃŃt

0.07

 sometimes

0.06

ys

0.06

 know

0.06

 biáº¿t

0.06

 Bale

0.06

 escape

0.06

 able

0.06

Activations Density 0.016%