INDEX

Explanations

No Explanations Found

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

 oncologist

0.86

нит

0.85

 semicolon

0.84

 clue

0.81

くなり

0.80

ت

0.77

 beaker

0.76

 creatinine

0.74

 toothbrush

0.72

 looting

0.72

POSITIVE LOGITS

ü

1.02

ühr

0.90

pia

0.87

alej

0.86

 Allerdings

0.86

ilie

0.86

arete

0.85

ügel

0.85

<0x80>

0.85

crossentropy

0.85

Activations Density 0.000%

No Known Activations