INDEX

Explanations

mentions of elevator-related terms

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagMode

-0.83

reonine

-0.65

 FetchType

-0.58

quiel

-0.57

 linkovi

-0.57

География

-0.57

Shining

-0.56

tispiece

-0.56

脚注の使い方

-0.56

Referensi

-0.55

POSITIVE LOGITS

 sens

1.66

 Sens

1.66

Sens

1.61

sens

1.55

 elevator

1.00

 restrictive

0.93

SENS

0.77

vens

0.77

 elevators

0.76

 SENS

0.75

Activations Density 0.005%