INDEX
Explanations
proper nouns or entities containing the word 'Tab'
references to specific tablet models
New Auto-Interp
Negative Logits
女
-0.82
Weasley
-0.72
EMENT
-0.72
IGH
-0.69
Colossus
-0.69
éĹĺ
-0.67
llor
-0.67
OHN
-0.66
Cornel
-0.66
Emin
-0.65
POSITIVE LOGITS
bed
1.05
atha
0.98
bing
0.93
rah
0.89
ram
0.89
oola
0.89
amba
0.88
atari
0.88
ulous
0.86
riz
0.86
Activations Density 0.017%