INDEX

Explanations

references to time, particularly phrases indicating the beginnings or early stages of events or entities

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Step

-0.07

_MPI

-0.07

 Step

-0.07

roke

-0.06

 Style

-0.06

_step

-0.06

robots

-0.06

_Style

-0.06

_entities

-0.06

 Entities

-0.05

POSITIVE LOGITS

 stages

0.14

 months

0.13

 weeks

0.12

 thro

0.12

 days

0.12

 portions

0.12

 parts

0.12

 portion

0.12

 stretches

0.12

 phases

0.11

Activations Density 0.015%