instances of the word "Well" indicating conversational transitions or emphasis

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

noop

-0.08

inosaur

-0.07

alc

-0.07

akra

-0.07

ache

-0.07

vt

-0.07

juana

-0.07

ideographic

-0.07

EMON

-0.07

ãĤ¾

-0.06

POSITIVE LOGITS

spring

0.08

ington

0.07

come

0.07

-known

0.07

aken

0.07

azor

0.06

idge

0.06

Activations Density 0.010%