INDEX

Explanations

socio-political concepts and narrative structures

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

ING

1.15

neath

1.14

ings

0.99

skl

0.96

 discrete

0.94

 flexion

0.93

 nutrients

0.93

िंग

0.92

 sturdy

0.91

 frantic

0.90

POSITIVE LOGITS

 کننده

1.08

О

1.07

eV

1.04

ervasyon

1.04

लाब

1.01

ᅴ

1.01

 оюндары

1.01

uée

1.00

৮

1.00

ère

0.98

Activations Density 0.028%