INDEX

Explanations

explaining or showing concepts

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

මට

0.40

 dynamic

0.37

动态

0.37

मला

0.37

 దృష్టి

0.37

情报

0.36

matical

0.36

 dinam

0.36

 oscuridad

0.36

 dynamics

0.35

POSITIVE LOGITS

 explaining

0.49

 explanation

0.46

explanation

0.45

 explicando

0.43

 Explanation

0.42

 показывать

0.42

สง

0.41

showing

0.41

 erklärt

0.40

 erklären

0.40

Activations Density 0.000%