INDEX
Explanations
terms related to distress or negative emotions
emotional reactions and mental states related to disappointment and despair
New Auto-Interp
Negative Logits
Kinnikuman
-0.64
amen
-0.63
sophistication
-0.62
enium
-0.62
frey
-0.59
ppa
-0.59
farmland
-0.59
convergence
-0.59
casinos
-0.58
minster
-0.57
POSITIVE LOGITS
ption
0.94
owship
0.92
untled
0.87
atives
0.86
essional
0.84
isitions
0.82
ptive
0.81
achment
0.77
ociate
0.76
ogyn
0.73
Activations Density 0.049%