INDEX

Explanations

falsely claiming, blatant, identify, assumed, information

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

 হীরু

1.19

uş

1.19

 computadora

1.17

<unused2006>

1.16

 álbum

1.15

 fría

1.15

 медици

1.14

 człowie

1.14

هی

1.13

 حاصل

1.13

POSITIVE LOGITS

all

1.01

 encoding

0.98

 Leave

0.97

 overwhelming

0.92

渟

0.91

のは

0.89

im

0.89

음

0.89

いき

0.88

0.86

Activations Density 0.029%