INDEX
Explanations
adjectives or verbs related to emotions or states of being in a calm or controlled manner
terms related to maintaining calmness, safety, and stability
New Auto-Interp
Negative Logits
repre
-0.63
owe
-0.62
lump
-0.61
apest
-0.60
Lot
-0.59
ouf
-0.59
DRAG
-0.57
asc
-0.57
FER
-0.57
fits
-0.57
POSITIVE LOGITS
indefinitely
0.93
until
0.93
till
0.91
whilst
0.85
amid
0.82
lest
0.80
despite
0.79
amidst
0.78
forever
0.76
throughout
0.74
Activations Density 0.105%