INDEX

Explanations

neural network linguistics

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

 ativos

0.38

 impartiality

0.38

 impartial

0.37

fug

0.36

美術

0.36

 수학

0.36

绘画

0.36

ký

0.36

毓

0.35

醣

0.35

POSITIVE LOGITS

 Literary

0.70

 linguistics

0.69

 Linguistics

0.68

 literary

0.65

 Linguistic

0.64

 linguistic

0.61

文学

0.58

 Lingu

0.57

 литератур

0.55

 lingu

0.55

Activations Density 0.098%