INDEX
Explanations
adjectives describing different circumstances or conditions
terms related to legal and political contexts
New Auto-Interp
Negative Logits
ocre
-0.77
enes
-0.73
aturdays
-0.68
belie
-0.67
okemon
-0.67
uckland
-0.65
nerds
-0.62
nervously
-0.62
utonium
-0.61
ffen
-0.61
POSITIVE LOGITS
ausp
1.19
guise
0.99
ħĭ
0.97
supervision
0.96
microscope
0.91
circumstances
0.81
ranch
0.80
Radar
0.80
rules
0.79
umbrella
0.78
Activations Density 0.175%