INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 suck

0.14

 christian

0.13

 Christian

0.12

 arasındaki

0.12

 가운데

0.12

 között

0.12

 chrét

0.12

 sucked

0.12

篌

0.11

 starts

0.11

POSITIVE LOGITS

maximal

0.14

RIOT

0.13

antiate

0.13

outputs

0.13

 únicos

0.13

 RICO

0.13

level

0.13

 ஓடுப

0.13

 suffices

0.13

gradients

0.13

Activations Density 1.329%

No Known Activations