INDEX
Explanations
phrases related to declarations or efforts in fighting a specific cause or issue
phrases involving the concept of "war on" various social issues or challenges
New Auto-Interp
Negative Logits
SourceFile
-0.94
Kay
-0.87
ItemImage
-0.81
auga
-0.79
ahime
-0.77
NH
-0.77
rete
-0.76
mere
-0.76
DH
-0.74
address
-0.74
POSITIVE LOGITS
behalf
0.81
etime
0.75
ruining
0.71
earth
0.70
Armageddon
0.70
wheels
0.68
eering
0.66
terror
0.65
impulse
0.64
preserving
0.63
Activations Density 0.068%