INDEX

Explanations

decreases linearly down

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lowering

-0.10

wert

-0.10

 ï½²

-0.09

apg

-0.09

WEEN

-0.09

 asympt

-0.09

 lowered

-0.09

 morph

-0.08

 downhill

-0.08

_backward

-0.08

POSITIVE LOGITS

 bell

0.18

fal

0.16

bell

0.15

 exponent

0.14

 initially

0.13

è¿ħ

0.13

igmoid

0.13

exp

0.13

ponential

0.13

log

0.12

Activations Density 0.092%