INDEX
Explanations
phrases starting with conjunctions such as 'so', 'and', 'but', and 'or'
pronouns and connecting words that indicate speaker orientation and personal expression
New Auto-Interp
Negative Logits
Lyme
-0.61
NES
-0.58
)))
-0.58
Ranch
-0.57
Duc
-0.56
Reef
-0.55
Vita
-0.54
crop
-0.54
Bat
-0.54
unsus
-0.53
POSITIVE LOGITS
ulty
1.00
theless
0.95
etheless
0.92
zbollah
0.91
selves
0.91
ngth
0.91
icularly
0.89
initely
0.87
mosp
0.87
etheus
0.87
Activations Density 0.219%